Search

The flat lensless camera design reduces the camera size and weight significantly. In this design, the camera lens is replaced by another optical element that interferes with the incoming light. The image is recovered from the raw sensor measurements using a reconstruction algorithm. Yet, the quality of the reconstructed images is not satisfactory. To mitigate this, we propose utilizing a pre-trained diffusion model with a control network and a learned separable transformation for reconstruction. This allows us to build a prototype flat camera with high-quality imaging, presenting state-of-the-art results in both terms of quality and perceptuality. We demonstrate its ability to leverage also textual descriptions of the captured scene to further enhance reconstruction. Our reconstruction method which leverages the strong capabilities of a pre-trained diffusion model can be used in other imaging systems for improved reconstruction results.

This work introduces a new framework, ProtoSAM, for one-shot medical image segmentation. It combines the use of prototypical networks, known for few-shot segmentation, with SAM - a natural image foundation model. The method proposed creates an initial coarse segmentation mask using the ALPnet prototypical network, augmented with a DINOv2 encoder. Following the extraction of an initial mask, prompts are extracted, such as points and bounding boxes, which are then input into the Segment Anything Model (SAM). State-of-the-art results are shown on several medical image datasets and demonstrate automated segmentation capabilities using a single image example (one shot) with no need for fine-tuning of the foundation model. Our code is available at: https://github.com/levayz/ProtoSAM, Comment: 12 pages, 3 figures, 4 tables, code: https://github.com/levayz/ProtoSAM

Chest X-rays or chest radiography (CXR), commonly used for medical diagnostics, typically enables limited imaging compared to computed tomography (CT) scans, which offer more detailed and accurate three-dimensional data, particularly contrast-enhanced scans like CT Pulmonary Angiography (CTPA). However, CT scans entail higher costs, greater radiation exposure, and are less accessible than CXRs. In this work we explore cross-modal translation from a 2D low contrast-resolution X-ray input to a 3D high contrast and spatial-resolution CTPA scan. Driven by recent advances in generative AI, we introduce a novel diffusion-based approach to this task. We evaluate the models performance using both quantitative metrics and qualitative feedback from radiologists, ensuring diagnostic relevance of the generated images. Furthermore, we employ the synthesized 3D images in a classification framework and show improved AUC in a PE categorization task, using the initial CXR input. The proposed method is generalizable and capable of performing additional cross-modality translations in medical imaging. It may pave the way for more accessible and cost-effective advanced diagnostic tools. The code for this project is available: https://github.com/NoaCahan/X-ray2CTPA ., Comment: preprint, project code: https://github.com/NoaCahan/X-ray2CTPA

Long-range sequence processing poses a significant challenge for Transformers due to their quadratic complexity in input length. A promising alternative is Mamba, which demonstrates high performance and achieves Transformer-level capabilities while requiring substantially fewer computational resources. In this paper we explore the length-generalization capabilities of Mamba, which we find to be relatively limited. Through a series of visualizations and analyses we identify that the limitations arise from a restricted effective receptive field, dictated by the sequence length used during training. To address this constraint, we introduce DeciMamba, a context-extension method specifically designed for Mamba. This mechanism, built on top of a hidden filtering mechanism embedded within the S6 layer, enables the trained model to extrapolate well even without additional training. Empirical experiments over real-world long-range NLP tasks show that DeciMamba can extrapolate to context lengths that are 25x times longer than the ones seen during training, and does so without utilizing additional computational resources. We will release our code and models., Comment: Link To Official Implementation: https://github.com/assafbk/DeciMamba

Comparing two images in terms of Commonalities and Differences (CaD) is a fundamental human capability that forms the basis of advanced visual reasoning and interpretation. It is essential for the generation of detailed and contextually relevant descriptions, performing comparative analysis, novelty detection, and making informed decisions based on visual data. However, surprisingly, little attention has been given to these fundamental concepts in the best current mimic of human visual intelligence - Large Multimodal Models (LMMs). We develop and contribute a new two-phase approach CaD-VI for collecting synthetic visual instructions, together with an instruction-following dataset CaD-Inst containing 349K image pairs with CaD instructions collected using CaD-VI. Our approach significantly improves the CaD spotting capabilities in LMMs, advancing the SOTA on a diverse set of related tasks by up to 17.5%. It is also complementary to existing difference-only instruction datasets, allowing automatic targeted refinement of those resources increasing their effectiveness for CaD tuning by up to 10%. Additionally, we propose an evaluation benchmark with 7.5K open-ended QAs to assess the CaD understanding abilities of LMMs., Comment: Project page: https://wlin-at.github.io/cad_vi ; Huggingface dataset repo: https://huggingface.co/datasets/wlin21at/CaD-Inst

Having large amounts of annotated data significantly impacts the effectiveness of deep neural networks. However, the annotation task can be very expensive in some domains, such as medical data. Thus, it is important to select the data to be annotated wisely, which is known as the subset selection problem. We investigate the relationship between subset selection and neural network pruning, which is more widely studied, and establish a correspondence between them. Leveraging insights from network pruning, we propose utilizing the norm criterion of neural network features to improve subset selection methods. We empirically validate our proposed strategy on various networks and datasets, demonstrating enhanced accuracy. This shows the potential of employing pruning tools for subset selection.

Distributed Denial of Service (DDoS) attacks are getting increasingly harmful to the Internet, showing no signs of slowing down. Developing an accurate detection mechanism to thwart DDoS attacks is still a big challenge due to the rich variety of these attacks and the emergence of new attack vectors. In this paper, we propose a new tree-based DDoS detection approach that operates on a flow as a stream structure, rather than the traditional fixed-size record structure containing aggregated flow statistics. Although aggregated flow records have gained popularity over the past decade, providing an effective means for flow-based intrusion detection by inspecting only a fraction of the total traffic volume, they are inherently constrained. Their detection precision is limited not only by the lack of packet payloads, but also by their structure, which is unable to model fine-grained inter-packet relations, such as packet order and temporal relations. Additionally, inferring aggregated flow statistics must wait for the complete flow to end. Here we show that considering flow inputs as variable-length streams composed of their associated packet headers, allows for very accurate and fast detection of malicious flows. We evaluate our proposed strategy on the CICDDoS2019 and CICIDS2017 datasets, which contain a comprehensive variety of DDoS attacks. Our approach matches or exceeds existing machine learning techniques' accuracy, including state-of-the-art deep learning methods. Furthermore, our method achieves significantly earlier detection, e.g., with CICDDoS2019 detection based on the first 2 packets, which corresponds to an average time-saving of 99.79% and uses only 4--6% of the traffic volume.

Phase-coded imaging is a computational imaging method designed to tackle tasks such as passive depth estimation and extended depth of field (EDOF) using depth cues inserted during image capture. Most of the current deep learning-based methods for depth estimation or all-in-focus imaging require a training dataset with high-quality depth maps and an optimal focus point at infinity for all-in-focus images. Such datasets are difficult to create, usually synthetic, and require external graphic programs. We propose a new method named "Deep Phase Coded Image Prior" (DPCIP) for jointly recovering the depth map and all-in-focus image from a coded-phase image using solely the captured image and the optical information of the imaging system. Our approach does not depend on any specific dataset and surpasses prior supervised techniques utilizing the same imaging system. This improvement is achieved through the utilization of a problem formulation based on implicit neural representation (INR) and deep image prior (DIP). Due to our zero-shot method, we overcome the barrier of acquiring accurate ground-truth data of depth maps and all-in-focus images for each new phase-coded system introduced. This allows focusing mainly on developing the imaging system, and not on ground-truth data collection.

Deep learning models have emerged as the cornerstone of medical image segmentation, but their efficacy hinges on the availability of extensive manually labeled datasets and their adaptability to unforeseen categories remains a challenge. Few-shot segmentation (FSS) offers a promising solution by endowing models with the capacity to learn novel classes from limited labeled examples. A leading method for FSS is ALPNet, which compares features between the query image and the few available support segmented images. A key question about using ALPNet is how to design its features. In this work, we delve into the potential of using features from DINOv2, which is a foundational self-supervised learning model in computer vision. Leveraging the strengths of ALPNet and harnessing the feature extraction capabilities of DINOv2, we present a novel approach to few-shot segmentation that not only enhances performance but also paves the way for more robust and adaptable medical image analysis.

Web-scale training on paired text-image data is becoming increasingly central to multimodal learning, but is challenged by the highly noisy nature of datasets in the wild. Standard data filtering approaches succeed in removing mismatched text-image pairs, but permit semantically related but highly abstract or subjective text. These approaches lack the fine-grained ability to isolate the most concrete samples that provide the strongest signal for learning in a noisy dataset. In this work, we propose a new metric, image caption concreteness, that evaluates caption text without an image reference to measure its concreteness and relevancy for use in multimodal learning. Our approach leverages strong foundation models for measuring visual-semantic information loss in multimodal representations. We demonstrate that this strongly correlates with human evaluation of concreteness in both single-word and sentence-level texts. Moreover, we show that curation using ICC complements existing approaches: It succeeds in selecting the highest quality samples from multimodal web-scale datasets to allow for efficient training in resource-constrained settings., Comment: Accepted to ACL 2024 (Finding). For Project webpage, see https://moranyanuka.github.io/icc/

In modern machine learning, models can often fit training data in numerous ways, some of which perform well on unseen (test) data, while others do not. Remarkably, in such cases gradient descent frequently exhibits an implicit bias that leads to excellent performance on unseen data. This implicit bias was extensively studied in supervised learning, but is far less understood in optimal control (reinforcement learning). There, learning a controller applied to a system via gradient descent is known as policy gradient, and a question of prime importance is the extent to which a learned controller extrapolates to unseen initial states. This paper theoretically studies the implicit bias of policy gradient in terms of extrapolation to unseen initial states. Focusing on the fundamental Linear Quadratic Regulator (LQR) problem, we establish that the extent of extrapolation depends on the degree of exploration induced by the system when commencing from initial states included in training. Experiments corroborate our theory, and demonstrate its conclusions on problems beyond LQR, where systems are non-linear and controllers are neural networks. We hypothesize that real-world optimal control may be greatly improved by developing methods for informed selection of initial states to train on., Comment: Accepted to ICML 2024

Transformers have achieved state-of-the-art performance in language modeling tasks. However, the reasons behind their tremendous success are still unclear. In this paper, towards a better understanding, we train a Transformer model on a simple next token prediction task, where sequences are generated as a first-order autoregressive process $s_{t+1} = W s_t$. We show how a trained Transformer predicts the next token by first learning $W$ in-context, then applying a prediction mapping. We call the resulting procedure in-context autoregressive learning. More precisely, focusing on commuting orthogonal matrices $W$, we first show that a trained one-layer linear Transformer implements one step of gradient descent for the minimization of an inner objective function, when considering augmented tokens. When the tokens are not augmented, we characterize the global minima of a one-layer diagonal linear multi-head Transformer. Importantly, we exhibit orthogonality between heads and show that positional encoding captures trigonometric relations in the data. On the experimental side, we consider the general case of non-commuting orthogonal matrices and generalize our theoretical findings., Comment: 20 pages ICML 2024

In recent years, the neural radiance field (NeRF) model has gained popularity due to its ability to recover complex 3D scenes. Following its success, many approaches proposed different NeRF representations in order to further improve both runtime and performance. One such example is Triplane, in which NeRF is represented using three 2D feature planes. This enables easily using existing 2D neural networks in this framework, e.g., to generate the three planes. Despite its advantage, the triplane representation lagged behind in its 3D recovery quality compared to NeRF solutions. In this work, we propose TriNeRFLet, a 2D wavelet-based multiscale triplane representation for NeRF, which closes the 3D recovery performance gap and is competitive with current state-of-the-art methods. Building upon the triplane framework, we also propose a novel super-resolution (SR) technique that combines a diffusion model with TriNeRFLet for improving NeRF resolution., Comment: Accepted to ECCV 2024. Webpage link: https://rajaeekh.github.io/trinerflet-web

Vision-Language models (VLMs) have proved effective at aligning image and text representations, producing superior zero-shot results when transferred to many downstream tasks. However, these representations suffer some key shortcomings in Compositional Language Concepts (CLC) understanding such as recognizing objects' attributes, states, and relations between different objects. Moreover, VLMs typically have poor interpretability, making it challenging to debug and mitigate compositional-understanding failures. In this work, we introduce the Tree-augmented Vision-Language (3VL) model architecture and training technique accompanied by our proposed Anchor inference method and Differential Relevance (DiRe) interpretability tool. By expanding the text of an arbitrary image-text pair into a hierarchical tree structure using language analysis tools, 3VL allows inducing this structure into the visual representation learned by the model, enhancing its interpretability and compositional reasoning. Additionally, we show how Anchor, a simple technique for text unification, can be employed to filter nuisance factors while increasing CLC understanding performance, e.g., on the fundamental VL-Checklist benchmark. We also exhibit how DiRe, which performs a differential comparison between VLM relevancy maps, enables us to generate compelling visualizations of the reasons for a model's success or failure.

The recent success of learning-based algorithms can be greatly attributed to the immense amount of annotated data used for training. Yet, many datasets lack annotations due to the high costs associated with labeling, resulting in degraded performances of deep learning methods. Self-supervised learning is frequently adopted to mitigate the reliance on massive labeled datasets since it exploits unlabeled data to learn relevant feature representations. In this work, we propose SS-StyleGAN, a self-supervised approach for image annotation and classification suitable for extremely small annotated datasets. This novel framework adds self-supervision to the StyleGAN architecture by integrating an encoder that learns the embedding to the StyleGAN latent space, which is well-known for its disentangled properties. The learned latent space enables the smart selection of representatives from the data to be labeled for improved classification performance. We show that the proposed method attains strong classification results using small labeled datasets of sizes 50 and even 10. We demonstrate the superiority of our approach for the tasks of COVID-19 and liver tumor pathology identification., Comment: Accepted to IEEE Transactions on Medical Imaging

Image reconstruction from noisy sensor measurements is a challenging problem. Many solutions have been proposed for it, where the main approach is learning good natural images prior along with modeling the true statistics of the noise in the scene. In the presence of very low lighting conditions, such approaches are usually not enough, and additional information is required, e.g., in the form of using multiple captures. We suggest as an alternative to add a description of the scene as prior, which can be easily done by the photographer capturing the scene. Inspired by the remarkable success of diffusion models for image generation, using a text-guided diffusion model we show that adding image caption information significantly improves image denoising and reconstruction on both synthetic and real-world images.

Deep learning, in general, focuses on training a neural network from large labeled datasets. Yet, in many cases there is value in training a network just from the input at hand. This is particularly relevant in many signal and image processing problems where training data is scarce and diversity is large on the one hand, and on the other, there is a lot of structure in the data that can be exploited. Using this information is the key to deep internal-learning strategies, which may involve training a network from scratch using a single input or adapting an already trained network to a provided input example at inference time. This survey paper aims at covering deep internal-learning techniques that have been proposed in the past few years for these two important directions. While our main focus will be on image processing problems, most of the approaches that we survey are derived for general signals (vectors with recurring patterns that can be distinguished from noise) and are therefore applicable to other modalities., Comment: Accepted to IEEE Signal Processing Magazine

While recent years have seen rapid progress in image-conditioned text generation, image captioning still suffers from the fundamental issue of hallucinations, namely, the generation of spurious details that cannot be inferred from the given image. Existing methods largely use closed-vocabulary object lists to mitigate or evaluate hallucinations in image captioning, ignoring the long-tailed nature of hallucinations that occur in practice. To this end, we propose a framework for addressing hallucinations in image captioning in the open-vocabulary setting. Our framework includes a new benchmark, OpenCHAIR, that leverages generative foundation models to evaluate open-vocabulary object hallucinations for image captioning, surpassing the popular and similarly-sized CHAIR benchmark in both diversity and accuracy. Furthermore, to mitigate open-vocabulary hallucinations without using a closed object list, we propose MOCHa, an approach harnessing advancements in reinforcement learning. Our multi-objective reward function explicitly targets the trade-off between fidelity and adequacy in generations without requiring any strong supervision. MOCHa improves a large variety of image captioning models, as captured by our OpenCHAIR benchmark and other existing metrics. We will release our code and models., Comment: Website Link: https://assafbk.github.io/mocha/

The prominent success of neural networks, mainly in computer vision tasks, is increasingly shadowed by their sensitivity to small, barely perceivable adversarial perturbations in image input. In this work, we aim at explaining this vulnerability through the framework of sparsity. We show the connection between adversarial attacks and sparse representations, with a focus on explaining the universality and transferability of adversarial examples in neural networks. To this end, we show that sparse coding algorithms, and the neural network-based learned iterative shrinkage thresholding algorithm (LISTA) among them, suffer from this sensitivity, and that common attacks on neural networks can be expressed as attacks on the sparse representation of the input image. The phenomenon that we observe holds true also when the network is agnostic to the sparse representation and dictionary, and thus can provide a possible explanation for the universality and transferability of adversarial attacks. The code is available at https://github.com/danawr/adversarial_attacks_and_sparse_representations.

As neural networks become deeper, the redundancy within their parameters increases. This phenomenon has led to several methods that attempt to reduce the correlation between convolutional filters. We propose a computationally efficient regularization technique that encourages orthonormality between groups of filters within the same layer. Our experiments show that when incorporated into recent adaptation methods for diffusion models and vision transformers (ViTs), this regularization improves performance on downstream tasks. We further show improved robustness when group orthogonality is enforced during adversarial training. Our code is available at https://github.com/YoavKurtz/GOR., Comment: BMVC 2023

This paper introduces supervised learning techniques for real-time selection (triggering) of hadronically decaying tau leptons in proton-proton colliders. By implementing classic machine learning decision trees and advanced deep learning models, such as Multi-Layer Perceptron or residual neural networks, visible improvements in performance compared to standard threshold tau triggers are observed. We show how such an implementation may lower selection energy thresholds, thus contributing to increasing the sensitivity of searches for new phenomena in proton-proton collisions classified by low-energy tau leptons. Moreover, we analyze when it is better to use neural networks versus decision trees for tau triggers with conclusions relevant to other problems in physics.

Transfer learning is a valuable tool in deep learning as it allows propagating information from one "source dataset" to another "target dataset", especially in the case of a small number of training examples in the latter. Yet, discrepancies between the underlying distributions of the source and target data are commonplace and are known to have a substantial impact on algorithm performance. In this work we suggest novel information-theoretic approaches for the analysis of the performance of deep neural networks in the context of transfer learning. We focus on the task of semi-supervised transfer learning, in which unlabeled samples from the target dataset are available during network training on the source dataset. Our theory suggests that one may improve the transferability of a deep neural network by incorporating regularization terms on the target data based on information-theoretic quantities, namely the Mutual Information and the Lautum Information. We demonstrate the effectiveness of the proposed approaches in various semi-supervised transfer learning experiments., Comment: arXiv admin note: substantial text overlap with arXiv:1904.01670

The recently introduced Segment Anything Model (SAM) combines a clever architecture and large quantities of training data to obtain remarkable image segmentation capabilities. However, it fails to reproduce such results for Out-Of-Distribution (OOD) domains such as medical images. Moreover, while SAM is conditioned on either a mask or a set of points, it may be desirable to have a fully automatic solution. In this work, we replace SAM's conditioning with an encoder that operates on the same input image. By adding this encoder and without further fine-tuning SAM, we obtain state-of-the-art results on multiple medical images and video benchmarks. This new encoder is trained via gradients provided by a frozen SAM. For inspecting the knowledge within it, and providing a lightweight segmentation solution, we also learn to decode it into a mask by a shallow deconvolution network.

We present SENS, a novel method for generating and editing 3D models from hand-drawn sketches, including those of abstract nature. Our method allows users to quickly and easily sketch a shape, and then maps the sketch into the latent space of a part-aware neural implicit shape architecture. SENS analyzes the sketch and encodes its parts into ViT patch encoding, subsequently feeding them into a transformer decoder that converts them to shape embeddings suitable for editing 3D neural implicit shapes. SENS provides intuitive sketch-based generation and editing, and also succeeds in capturing the intent of the user's sketch to generate a variety of novel and expressive 3D shapes, even from abstract and imprecise sketches. Additionally, SENS supports refinement via part reconstruction, allowing for nuanced adjustments and artifact removal. It also offers part-based modeling capabilities, enabling the combination of features from multiple sketches to create more complex and customized 3D shapes. We demonstrate the effectiveness of our model compared to the state-of-the-art using objective metric evaluation criteria and a user study, both indicating strong performance on sketches with a medium level of abstraction. Furthermore, we showcase our method's intuitive sketch-based shape editing capabilities, and validate it through a usability study., Comment: 25 pages, 24 figures

Vision and Language (VL) models offer an effective method for aligning representation spaces of images and text, leading to numerous applications such as cross-modal retrieval, visual question answering, captioning, and more. However, the aligned image-text spaces learned by all the popular VL models are still suffering from the so-called `object bias' - their representations behave as `bags of nouns', mostly ignoring or downsizing the attributes, relations, and states of objects described/appearing in texts/images. Although some great attempts at fixing these `compositional reasoning' issues were proposed in the recent literature, the problem is still far from being solved. In this paper, we uncover two factors limiting the VL models' compositional reasoning performance. These two factors are properties of the paired VL dataset used for finetuning and pre-training the VL model: (i) the caption quality, or in other words `image-alignment', of the texts; and (ii) the `density' of the captions in the sense of mentioning all the details appearing on the image. We propose a fine-tuning approach for automatically treating these factors leveraging a standard VL dataset (CC3M). Applied to CLIP, we demonstrate its significant compositional reasoning performance increase of up to $\sim27\%$ over the base model, up to $\sim20\%$ over the strongest baseline, and by $6.7\%$ on average.

The lottery ticket hypothesis (LTH) has increased attention to pruning neural networks at initialization. We study this problem in the linear setting. We show that finding a sparse mask at initialization is equivalent to the sketching problem introduced for efficient matrix multiplication. This gives us tools to analyze the LTH problem and gain insights into it. Specifically, using the mask found at initialization, we bound the approximation error of the pruned linear model at the end of training. We theoretically justify previous empirical evidence that the search for sparse networks may be data independent. By using the sketching perspective, we suggest a generic improvement to existing algorithms for pruning at initialization, which we show to be beneficial in the data-independent case., Comment: 20 pages

This work bridges two important concepts: the Neural Tangent Kernel (NTK), which captures the evolution of deep neural networks (DNNs) during training, and the Neural Collapse (NC) phenomenon, which refers to the emergence of symmetry and structure in the last-layer features of well-trained classification DNNs. We adopt the natural assumption that the empirical NTK develops a block structure aligned with the class labels, i.e., samples within the same class have stronger correlations than samples from different classes. Under this assumption, we derive the dynamics of DNNs trained with mean squared (MSE) loss and break them into interpretable phases. Moreover, we identify an invariant that captures the essence of the dynamics, and use it to prove the emergence of NC in DNNs with block-structured NTK. We provide large-scale numerical experiments on three common DNN architectures and three benchmark datasets to support our theory.

Denoising Diffusion Probabilistic Models (DDPM) have recently gained significant attention. DDPMs compose a Markovian process that begins in the data domain and gradually adds noise until reaching pure white noise. DDPMs generate high-quality samples from complex data distributions by defining an inverse process and training a deep neural network to learn this mapping. However, these models are inefficient because they require many diffusion steps to produce aesthetically pleasing samples. Additionally, unlike generative adversarial networks (GANs), the latent space of diffusion models is less interpretable. In this work, we propose to generalize the denoising diffusion process into an Upsampling Diffusion Probabilistic Model (UDPM). In the forward process, we reduce the latent variable dimension through downsampling, followed by the traditional noise perturbation. As a result, the reverse process gradually denoises and upsamples the latent variable to produce a sample from the data distribution. We formalize the Markovian diffusion processes of UDPM and demonstrate its generation capabilities on the popular FFHQ, AFHQv2, and CIFAR10 datasets. UDPM generates images with as few as three network evaluations, whose overall computational cost is less than a single DDPM or EDM step, while achieving an FID score of 6.86. This surpasses current state-of-the-art efficient diffusion models that use a single denoising step for sampling. Additionally, UDPM offers an interpretable and interpolable latent space, which gives it an advantage over traditional DDPMs. Our code is available online: \url{https://github.com/shadyabh/UDPM/}

Label-efficient and reliable semantic segmentation is essential for many real-life applications, especially for industrial settings with high visual diversity, such as waste sorting. In industrial waste sorting, one of the biggest challenges is the extreme diversity of the input stream depending on factors like the location of the sorting facility, the equipment available in the facility, and the time of year, all of which significantly impact the composition and visual appearance of the waste stream. These changes in the data are called ``visual domains'', and label-efficient adaptation of models to such domains is needed for successful semantic segmentation of industrial waste. To test the abilities of computer vision models on this task, we present the VisDA 2022 Challenge on Domain Adaptation for Industrial Waste Sorting. Our challenge incorporates a fully-annotated waste sorting dataset, ZeroWaste, collected from two real material recovery facilities in different locations and seasons, as well as a novel procedurally generated synthetic waste sorting dataset, SynthWaste. In this competition, we aim to answer two questions: 1) can we leverage domain adaptation techniques to minimize the domain gap? and 2) can synthetic data augmentation improve performance on this task and help adapt to changing data distributions? The results of the competition show that industrial waste detection poses a real domain adaptation problem, that domain generalization techniques such as augmentations, ensembling, etc., improve the overall performance on the unlabeled target domain examples, and that leveraging synthetic data effectively remains an open problem. See https://ai.bu.edu/visda-2022/, Comment: Proceedings of Machine Learning Research

Recent breakthroughs in text-guided image generation have led to remarkable progress in the field of 3D synthesis from text. By optimizing neural radiance fields (NeRF) directly from text, recent methods are able to produce remarkable results. Yet, these methods are limited in their control of each object's placement or appearance, as they represent the scene as a whole. This can be a major issue in scenarios that require refining or manipulating objects in the scene. To remedy this deficit, we propose a novel GlobalLocal training framework for synthesizing a 3D scene using object proxies. A proxy represents the object's placement in the generated scene and optionally defines its coarse geometry. The key to our approach is to represent each object as an independent NeRF. We alternate between optimizing each NeRF on its own and as part of the full scene. Thus, a complete representation of each object can be learned, while also creating a harmonious scene with style and lighting match. We show that using proxies allows a wide variety of editing options, such as adjusting the placement of each independent object, removing objects from a scene, or refining an object. Our results show that Set-the-Scene offers a powerful solution for scene synthesis and manipulation, filling a crucial gap in controllable text-to-3D synthesis., Comment: project page at https://danacohen95.github.io/Set-the-Scene/

Self-supervised models allow (pre-)training on unlabeled data and therefore have the potential to overcome the need for large annotated cohorts. One leading self-supervised model is the masked autoencoder (MAE) which was developed on natural imaging data. The MAE is masking out a high fraction of visual transformer (ViT) input patches, to then recover the uncorrupted images as a pretraining task. In this work, we extend MAE to perform anomaly detection on breast magnetic resonance imaging (MRI). This new model, coined masked autoencoder for medical imaging (MAEMI) is trained on two non-contrast enhanced MRI sequences, aiming at lesion detection without the need for intravenous injection of contrast media and temporal image acquisition. During training, only non-cancerous images are presented to the model, with the purpose of localizing anomalous tumor regions during test time. We use a public dataset for model development. Performance of the architecture is evaluated in reference to subtraction images created from dynamic contrast enhanced (DCE)-MRI.

In this paper, we present TEXTure, a novel method for text-guided generation, editing, and transfer of textures for 3D shapes. Leveraging a pretrained depth-to-image diffusion model, TEXTure applies an iterative scheme that paints a 3D model from different viewpoints. Yet, while depth-to-image models can create plausible textures from a single viewpoint, the stochastic nature of the generation process can cause many inconsistencies when texturing an entire 3D object. To tackle these problems, we dynamically define a trimap partitioning of the rendered image into three progression states, and present a novel elaborated diffusion sampling process that uses this trimap representation to generate seamless textures from different views. We then show that one can transfer the generated texture maps to new 3D geometries without requiring explicit surface-to-surface mapping, as well as extract semantic textures from a set of images without requiring any explicit reconstruction. Finally, we show that TEXTure can be used to not only generate new textures but also edit and refine existing textures using either a text prompt or user-provided scribbles. We demonstrate that our TEXTuring method excels at generating, transferring, and editing textures through extensive evaluation, and further close the gap between 2D image generation and 3D texturing., Comment: Project page available at https://texturepaper.github.io/TEXTurePaper/

In recent years, denoising diffusion models have demonstrated outstanding image generation performance. The information on natural images captured by these models is useful for many image reconstruction applications, where the task is to restore a clean image from its degraded observations. In this work, we propose a conditional sampling scheme that exploits the prior learned by diffusion models while retaining agreement with the observations. We then combine it with a novel approach for adapting pretrained diffusion denoising networks to their input. We examine two adaption strategies: the first uses only the degraded image, while the second, which we advocate, is performed using images that are ``nearest neighbors'' of the degraded image, retrieved from a diverse dataset using an off-the-shelf visual-language model. To evaluate our method, we test it on two state-of-the-art publicly available diffusion models, Stable Diffusion and Guided Diffusion. We show that our proposed `adaptive diffusion for image reconstruction' (ADIR) approach achieves a significant improvement in the super-resolution, deblurring, and text-based editing tasks., Comment: Our code and additional results are available online in the project page https://shadyabh.github.io/ADIR/

We propose using Masked Auto-Encoder (MAE), a transformer model self-supervisedly trained on image inpainting, for anomaly detection (AD). Assuming anomalous regions are harder to reconstruct compared with normal regions. MAEDAY is the first image-reconstruction-based anomaly detection method that utilizes a pre-trained model, enabling its use for Few-Shot Anomaly Detection (FSAD). We also show the same method works surprisingly well for the novel tasks of Zero-Shot AD (ZSAD) and Zero-Shot Foreign Object Detection (ZSFOD), where no normal samples are available. Code is available at https://github.com/EliSchwartz/MAEDAY ., Comment: Computer Vision and Image Understanding, 2024

In Deep Image Prior (DIP), a Convolutional Neural Network (CNN) is fitted to map a latent space to a degraded (e.g. noisy) image but in the process learns to reconstruct the clean image. This phenomenon is attributed to CNN's internal image-prior. We revisit the DIP framework, examining it from the perspective of a neural implicit representation. Motivated by this perspective, we replace the random or learned latent with Fourier-Features (Positional Encoding). We show that thanks to the Fourier features properties, we can replace the convolution layers with simple pixel-level MLPs. We name this scheme ``Positional Encoding Image Prior" (PIP) and exhibit that it performs very similarly to DIP on various image-reconstruction tasks with much less parameters required. Additionally, we demonstrate that PIP can be easily extended to videos, where 3D-DIP struggles and suffers from instability. Code and additional examples for all tasks, including videos, are available on the project page https://nimrodshabtay.github.io/PIP/

Vision and Language (VL) models have demonstrated remarkable zero-shot performance in a variety of tasks. However, some aspects of complex language understanding still remain a challenge. We introduce the collective notion of Structured Vision&Language Concepts (SVLC) which includes object attributes, relations, and states which are present in the text and visible in the image. Recent studies have shown that even the best VL models struggle with SVLC. A possible way of fixing this issue is by collecting dedicated datasets for teaching each SVLC type, yet this might be expensive and time-consuming. Instead, we propose a more elegant data-driven approach for enhancing VL models' understanding of SVLCs that makes more effective use of existing VL pre-training datasets and does not require any additional data. While automatic understanding of image structure still remains largely unsolved, language structure is much better modeled and understood, allowing for its effective utilization in teaching VL models. In this paper, we propose various techniques based on language structure understanding that can be used to manipulate the textual part of off-the-shelf paired VL datasets. VL models trained with the updated data exhibit a significant improvement of up to 15% in their SVLC understanding with only a mild degradation in their zero-shot capabilities both when training from scratch or fine-tuning a pre-trained model.

Text-guided image generation has progressed rapidly in recent years, inspiring major breakthroughs in text-guided shape generation. Recently, it has been shown that using score distillation, one can successfully text-guide a NeRF model to generate a 3D object. We adapt the score distillation to the publicly available, and computationally efficient, Latent Diffusion Models, which apply the entire diffusion process in a compact latent space of a pretrained autoencoder. As NeRFs operate in image space, a naive solution for guiding them with latent score distillation would require encoding to the latent space at each guidance step. Instead, we propose to bring the NeRF to the latent space, resulting in a Latent-NeRF. Analyzing our Latent-NeRF, we show that while Text-to-3D models can generate impressive results, they are inherently unconstrained and may lack the ability to guide or enforce a specific 3D structure. To assist and direct the 3D generation, we propose to guide our Latent-NeRF using a Sketch-Shape: an abstract geometry that defines the coarse structure of the desired object. Then, we present means to integrate such a constraint directly into a Latent-NeRF. This unique combination of text and shape guidance allows for increased control over the generation process. We also show that latent score distillation can be successfully applied directly on 3D meshes. This allows for generating high-quality textures on a given geometry. Our experiments validate the power of our different forms of guidance and the efficiency of using latent rendering. Implementation is available at https://github.com/eladrich/latent-nerf

Overparameterization in deep learning typically refers to settings where a trained neural network (NN) has representational capacity to fit the training data in many ways, some of which generalize well, while others do not. In the case of Recurrent Neural Networks (RNNs), there exists an additional layer of overparameterization, in the sense that a model may exhibit many solutions that generalize well for sequence lengths seen in training, some of which extrapolate to longer sequences, while others do not. Numerous works have studied the tendency of Gradient Descent (GD) to fit overparameterized NNs with solutions that generalize well. On the other hand, its tendency to fit overparameterized RNNs with solutions that extrapolate has been discovered only recently and is far less understood. In this paper, we analyze the extrapolation properties of GD when applied to overparameterized linear RNNs. In contrast to recent arguments suggesting an implicit bias towards short-term memory, we provide theoretical evidence for learning low-dimensional state spaces, which can also model long-term memory. Our result relies on a dynamical characterization which shows that GD (with small step size and near-zero initialization) strives to maintain a certain form of balancedness, as well as on tools developed in the context of the moment problem from statistics (recovery of a probability distribution from its moments). Experiments corroborate our theory, demonstrating extrapolation via learning low-dimensional state spaces with both linear and non-linear RNNs., Comment: Accepted to ICLR 2023, 9 pages, 2 figures plus supplementary

Diffusion models are a special type of generative model, capable of synthesising new data from a learnt distribution. We introduce DISPR, a diffusion-based model for solving the inverse problem of three-dimensional (3D) cell shape prediction from two-dimensional (2D) single cell microscopy images. Using the 2D microscopy image as a prior, DISPR is conditioned to predict realistic 3D shape reconstructions. To showcase the applicability of DISPR as a data augmentation tool in a feature-based single cell classification task, we extract morphological features from the red blood cells grouped into six highly imbalanced classes. Adding features from the DISPR predictions to the three minority classes improved the macro F1 score from $F1_\text{macro} = 55.2 \pm 4.6\%$ to $F1_\text{macro} = 72.2 \pm 4.9\%$. We thus demonstrate that diffusion models can be successfully applied to inverse biomedical problems, and that they learn to reconstruct 3D shapes with realistic morphological features from 2D microscopy images.

In this work, we suggest Kernel Filtering Linear Overparameterization (KFLO), where a linear cascade of filtering layers is used during training to improve network performance in test time. We implement this cascade in a kernel filtering fashion, which prevents the trained architecture from becoming unnecessarily deeper. This also allows using our approach with almost any network architecture and let combining the filtering layers into a single layer in test time. Thus, our approach does not add computational complexity during inference. We demonstrate the advantage of KFLO on various network models and datasets in supervised learning., Comment: Accepted to ICIP 2022. Code available at https://github.com/AmitHenig/KFLO

Member inference (MI) attacks aim to determine if a specific data sample was used to train a machine learning model. Thus, MI is a major privacy threat to models trained on private sensitive data, such as medical records. In MI attacks one may consider the black-box settings, where the model's parameters and activations are hidden from the adversary, or the white-box case where they are available to the attacker. In this work, we focus on the latter and present a novel MI attack for it that employs influence functions, or more specifically the samples' self-influence scores, to perform the MI prediction. We evaluate our attack on CIFAR-10, CIFAR-100, and Tiny ImageNet datasets, using versatile architectures such as AlexNet, ResNet, and DenseNet. Our attack method achieves new state-of-the-art results for both training with and without data augmentations. Code is available at https://github.com/giladcohen/sif_mi_attack.

Using synthetic data for training neural networks that achieve good performance on real-world data is an important task as it can reduce the need for costly data annotation. Yet, synthetic and real world data have a domain gap. Reducing this gap, also known as domain adaptation, has been widely studied in recent years. Closing the domain gap between the source (synthetic) and target (real) data by directly performing the adaptation between the two is challenging. In this work, we propose a novel two-stage framework for improving domain adaptation techniques on image data. In the first stage, we progressively train a multi-scale neural network to perform image translation from the source domain to the target domain. We denote the new transformed data as "Source in Target" (SiT). Then, we insert the generated SiT data as the input to any standard UDA approach. This new data has a reduced domain gap from the desired target domain, which facilitates the applied UDA approach to close the gap further. We emphasize the effectiveness of our method via a comparison to other leading UDA and image-to-image translation techniques when used as SiT generators. Moreover, we demonstrate the improvement of our framework with three state-of-the-art UDA methods for semantic segmentation, HRDA, DAFormer and ProDA, on two UDA tasks, GTA5 to Cityscapes and Synthia to Cityscapes., Comment: Code available at https://github.com/shahaf1313/ProCST

Rigid Point Cloud Registration (PCR) algorithms aim to estimate the 6-DOF relative motion between two point clouds, which is important in various fields, including autonomous driving. Recent years have seen a significant improvement in global PCR algorithms, i.e. algorithms that can handle a large relative motion. This has been demonstrated in various scenarios, including indoor scenes, but has only been minimally tested in the Automotive setting, where point clouds are produced by vehicle-mounted LiDAR sensors. In this work, we aim to answer questions that are important for automotive applications, including: which of the new algorithms is the most accurate, and which is fastest? How transferable are deep-learning approaches, e.g. what happens when you train a network with data from Boston, and run it in a vehicle in Singapore? How small can the overlap between point clouds be before the algorithms start to deteriorate? To what extent are the algorithms rotation invariant? Our results are at times surprising. When comparing robust parameter estimation methods for registration, we find that the fastest and most accurate is not one of the newest approaches. Instead, it is a modern variant of the well known RANSAC technique. We also suggest a new outlier filtering method, Grid-Prioritized Filtering (GPF), to further improve it. An additional contribution of this work is an algorithm for selecting challenging sets of frame-pairs from automotive LiDAR datasets. This enables meaningful benchmarking in the Automotive LiDAR setting, and can also improve training for learning algorithms., Comment: Accepted to the NeurIPS 2022 workshop on Machine Learning for Autonomous Driving. Project Page: https://github.com/AmnonDrory/LidarRegistration

We study the 2-D super-resolution multi-reference alignment (SR-MRA) problem: estimating an image from its down-sampled, circularly-translated, and noisy copies. The SR-MRA problem serves as a mathematical abstraction of the structure determination problem for biological molecules. Since the SR-MRA problem is ill-posed without prior knowledge, accurate image estimation relies on designing priors that well-describe the statistics of the images of interest. In this work, we build on recent advances in image processing, and harness the power of denoisers as priors of images. In particular, we suggest to use denoisers as projections, and design two computational frameworks to estimate the image: projected expectation-maximization and projected method of moments. We provide an efficient GPU implementation, and demonstrate the effectiveness of these algorithms by extensive numerical experiments on a wide range of parameters and images.

In a previous paper, we have introduced a deep learning neural network that should be able to detect the existence of very shallow periodic planetary transits in the presence of red noise. The network in that feasibility study would not provide any further details about the detected transits. The current paper completes this missing part. We present a neural network that tags samples that were obtained during transits. This is essentially similar to the task of identifying the semantic context of each pixel in an image -- an important task in computer vision, called `semantic segmentation', which is often performed by deep neural networks. The neural network we present makes use of novel deep learning concepts such as U-Nets, Generative Adversarial Networks (GAN), and adversarial loss. The resulting segmentation should allow further studies of the light curves which are tagged as containing transits. This approach towards the detection and study of very shallow transits is bound to play a significant role in future space-based transit surveys such as PLATO, which are specifically aimed to detect those extremely difficult cases of long-period shallow transits. Our segmentation network also adds to the growing toolbox of deep learning approaches which are being increasingly used in the study of exoplanets, but so far mainly for vetting transits, rather than their initial detection., Comment: 16 pages, 14 figures, accepted for publication in the Astronomical Journal

Generative Adversarial Networks (GANs) are very popular frameworks for generating high-quality data, and are immensely used in both the academia and industry in many domains. Arguably, their most substantial impact has been in the area of computer vision, where they achieve state-of-the-art image generation. This chapter gives an introduction to GANs, by discussing their principle mechanism and presenting some of their inherent problems during training and evaluation. We focus on these three issues: (1) mode collapse, (2) vanishing gradients, and (3) generation of low-quality images. We then list some architecture-variant and loss-variant GANs that remedy the above challenges. Lastly, we present two utilization examples of GANs for real-world applications: Data augmentation and face images generation.

Neural implicit fields are quickly emerging as an attractive representation for learning based techniques. However, adopting them for 3D shape modeling and editing is challenging. We introduce a method for $\mathbf{E}$diting $\mathbf{I}$mplicit $\mathbf{S}$hapes $\mathbf{T}$hrough $\mathbf{P}$art $\mathbf{A}$ware $\mathbf{G}$enera$\mathbf{T}$ion, permuted in short as SPAGHETTI. Our architecture allows for manipulation of implicit shapes by means of transforming, interpolating and combining shape segments together, without requiring explicit part supervision. SPAGHETTI disentangles shape part representation into extrinsic and intrinsic geometric information. This characteristic enables a generative framework with part-level control. The modeling capabilities of SPAGHETTI are demonstrated using an interactive graphical interface, where users can directly edit neural implicit shapes.

Fictional languages have become increasingly popular over the recent years appearing in novels, movies, TV shows, comics, and video games. While some of these fictional languages have a complete vocabulary, most do not. We propose a deep learning solution to the problem. Using style transfer and machine translation tools, we generate new words for a given target fictional language, while maintaining the style of its creator, hence extending this language vocabulary., Comment: 10 pages, 1 figure, NeurIPS Workshop on Machine Learning for Creativity and Design 2021

We introduce NeuralMLS, a space-based deformation technique, guided by a set of displaced control points. We leverage the power of neural networks to inject the underlying shape geometry into the deformation parameters. The goal of our technique is to enable a realistic and intuitive shape deformation. Our method is built upon moving least-squares (MLS), since it minimizes a weighted sum of the given control point displacements. Traditionally, the influence of each control point on every point in space (i.e., the weighting function) is defined using inverse distance heuristics. In this work, we opt to learn the weighting function, by training a neural network on the control points from a single input shape, and exploit the innate smoothness of neural networks. Our geometry-aware control point deformation is agnostic to the surface representation and quality; it can be applied to point clouds or meshes, including non-manifold and disconnected surface soups. We show that our technique facilitates intuitive piecewise smooth deformations, which are well suited for manufactured objects. We show the advantages of our approach compared to existing surface and space-based deformation techniques, both quantitatively and qualitatively., Comment: Eurographics 2022 Short Papers