Search

Latent diffusion models (LDMs) power state-of-the-art high-resolution generative image models. LDMs learn the data distribution in the latent space of an autoencoder (AE) and produce images by mapping the generated latents into RGB image space using the AE decoder. While this approach allows for efficient model training and sampling, it induces a disconnect between the training of the diffusion model and the decoder, resulting in a loss of detail in the generated images. To remediate this disconnect, we propose to leverage the internal features of the decoder to define a latent perceptual loss (LPL). This loss encourages the models to create sharper and more realistic images. Our loss can be seamlessly integrated with common autoencoders used in latent diffusion models, and can be applied to different generative modeling paradigms such as DDPM with epsilon and velocity prediction, as well as flow matching. Extensive experiments with models trained on three datasets at 256 and 512 resolution show improved quantitative -- with boosts between 6% and 20% in FID -- and qualitative results when using our perceptual loss., Comment: Pre-print

Large-scale training of latent diffusion models (LDMs) has enabled unprecedented quality in image generation. However, the key components of the best performing LDM training recipes are oftentimes not available to the research community, preventing apple-to-apple comparisons and hindering the validation of progress in the field. In this work, we perform an in-depth study of LDM training recipes focusing on the performance of models and their training efficiency. To ensure apple-to-apple comparisons, we re-implement five previously published models with their corresponding recipes. Through our study, we explore the effects of (i)~the mechanisms used to condition the generative model on semantic information (e.g., text prompt) and control metadata (e.g., crop size, random flip flag, etc.) on the model performance, and (ii)~the transfer of the representations learned on smaller and lower-resolution datasets to larger ones on the training efficiency and model performance. We then propose a novel conditioning mechanism that disentangles semantic and control metadata conditionings and sets a new state-of-the-art in class-conditional generation on the ImageNet-1k dataset -- with FID improvements of 7% on 256 and 8% on 512 resolutions -- as well as text-to-image generation on the CC12M dataset -- with FID improvements of 8% on 256 and 23% on 512 resolution., Comment: Accepted as a conference paper (poster) for NeurIPS 2024

Building world models that accurately and comprehensively represent the real world is the utmost aspiration for conditional image generative models as it would enable their use as world simulators. For these models to be successful world models, they should not only excel at image quality and prompt-image consistency but also ensure high representation diversity. However, current research in generative models mostly focuses on creative applications that are predominantly concerned with human preferences of image quality and aesthetics. We note that generative models have inference time mechanisms - or knobs - that allow the control of generation consistency, quality, and diversity. In this paper, we use state-of-the-art text-to-image and image-and-text-to-image models and their knobs to draw consistency-diversity-realism Pareto fronts that provide a holistic view on consistency-diversity-realism multi-objective. Our experiments suggest that realism and consistency can both be improved simultaneously; however there exists a clear tradeoff between realism/consistency and diversity. By looking at Pareto optimal points, we note that earlier models are better at representation diversity and worse in consistency/realism, and more recent models excel in consistency/realism while decreasing significantly the representation diversity. By computing Pareto fronts on a geodiverse dataset, we find that the first version of latent diffusion models tends to perform better than more recent models in all axes of evaluation, and there exist pronounced consistency-diversity-realism disparities between geographical regions. Overall, our analysis clearly shows that there is no best model and the choice of model should be determined by the downstream application. With this analysis, we invite the research community to consider Pareto fronts as an analytical tool to measure progress towards world models.

The abilities of large language models (LLMs) have recently progressed to unprecedented levels, paving the way to novel applications in a wide variety of areas. In computer vision, LLMs can be used to prime vision-language tasks such image captioning and visual question answering when coupled with pre-trained vision backbones. While different approaches have been explored to interface LLMs with ``perceptual backbones'' that process, e.g., visual or audio data, they are often explored for different tasks, different datasets, and using different perceptual backbones and language models, hindering direct comparison of the interfacing mechanisms. To remedy this lack of comparability between methods, we present an extensive experimental evaluation of different interfacing mechanisms, across multiple tasks (including image, video, and audio captioning as well as visual question answering), datasets and backbones, paying special attention to low-data settings. We find improved performance using existing mechanisms over state-of-the-art results, and identify a new interfacing mechanism that yields (near) optimal results across different tasks, while obtaining a 4x reduction in training time.

Despite the availability of large datasets for tasks like image classification and image-text alignment, labeled data for more complex recognition tasks, such as detection and segmentation, is less abundant. In particular, for instance segmentation annotations are time-consuming to produce, and the distribution of instances is often highly skewed across classes. While semi-supervised teacher-student distillation methods show promise in leveraging vast amounts of unlabeled data, they suffer from miscalibration, resulting in overconfidence in frequently represented classes and underconfidence in rarer ones. Additionally, these methods encounter difficulties in efficiently learning from a limited set of examples. We introduce a dual-strategy to enhance the teacher model's training process, substantially improving the performance on few-shot learning. Secondly, we propose a calibration correction mechanism that that enables the student model to correct the teacher's calibration errors. Using our approach, we observed marked improvements over a state-of-the-art supervised baseline performance on the LVIS dataset, with an increase of 2.8% in average precision (AP) and 10.3% gain in AP for rare classes., Comment: Appeared at the Practical ML for Low Resource Settings workshop at ICLR 2024

Vector quantization is a fundamental operation for data compression and vector search. To obtain high accuracy, multi-codebook methods represent each vector using codewords across several codebooks. Residual quantization (RQ) is one such method, which iteratively quantizes the error of the previous step. While the error distribution is dependent on previously-selected codewords, this dependency is not accounted for in conventional RQ as it uses a fixed codebook per quantization step. In this paper, we propose QINCo, a neural RQ variant that constructs specialized codebooks per step that depend on the approximation of the vector from previous steps. Experiments show that QINCo outperforms state-of-the-art methods by a large margin on several datasets and code sizes. For example, QINCo achieves better nearest-neighbor search accuracy using 12-byte codes than the state-of-the-art UNQ using 16 bytes on the BigANN1M and Deep1M datasets., Comment: To appear at ICML 2024

Semantic image synthesis, i.e., generating images from user-provided semantic label maps, is an important conditional image generation task as it allows to control both the content as well as the spatial layout of generated images. Although diffusion models have pushed the state of the art in generative image modeling, the iterative nature of their inference process makes them computationally demanding. Other approaches such as GANs are more efficient as they only need a single feed-forward pass for generation, but the image quality tends to suffer on large and diverse datasets. In this work, we propose a new class of GAN discriminators for semantic image synthesis that generates highly realistic images by exploiting feature backbone networks pre-trained for tasks such as image classification. We also introduce a new generator architecture with better context modeling and using cross-attention to inject noise into latent variables, leading to more diverse generated images. Our model, which we dub DP-SIMS, achieves state-of-the-art results in terms of image quality and consistency with the input label maps on ADE-20K, COCO-Stuff, and Cityscapes, surpassing recent diffusion models while requiring two orders of magnitude less compute for inference.

Image codecs are typically optimized to trade-off bitrate \vs distortion metrics. At low bitrates, this leads to compression artefacts which are easily perceptible, even when training with perceptual or adversarial losses. To improve image quality and remove dependency on the bitrate, we propose to decode with iterative diffusion models. We condition the decoding process on a vector-quantized image representation, as well as a global image description to provide additional context. We dub our model PerCo for 'perceptual compression', and compare it to state-of-the-art codecs at rates from 0.1 down to 0.003 bits per pixel. The latter rate is more than an order of magnitude smaller than those considered in most prior work, compressing a 512x768 Kodak image with less than 153 bytes. Despite this ultra-low bitrate, our approach maintains the ability to reconstruct realistic images. We find that our model leads to reconstructions with state-of-the-art visual quality as measured by FID and KID. As predicted by rate-distortion-perception theory, visual quality is less dependent on the bitrate than previous methods.

Although instance segmentation methods have improved considerably, the dominant paradigm is to rely on fully-annotated training images, which are tedious to obtain. To alleviate this reliance, and boost results, semi-supervised approaches leverage unlabeled data as an additional training signal that limits overfitting to the labeled samples. In this context, we present novel design choices to significantly improve teacher-student distillation models. In particular, we (i) improve the distillation approach by introducing a novel "guided burn-in" stage, and (ii) evaluate different instance segmentation architectures, as well as backbone networks and pre-training strategies. Contrary to previous work which uses only supervised data for the burn-in period of the student model, we also use guidance of the teacher model to exploit unlabeled data in the burn-in period. Our improved distillation approach leads to substantial improvements over previous state-of-the-art results. For example, on the Cityscapes dataset we improve mask-AP from 23.7 to 33.9 when using labels for 10\% of images, and on the COCO dataset we improve mask-AP from 18.3 to 34.1 when using labels for only 1\% of the training data., Comment: Accepted at the 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2024)

Deep convolutional networks are ubiquitous in computer vision, due to their excellent performance across different tasks for various domains. Models are, however, often trained in isolation for each task, failing to exploit relatedness between tasks and domains to learn more compact models that generalise better in low-data regimes. Multi-domain learning aims to handle related tasks, such as image classification across multiple domains, simultaneously. Previous work on this problem explored the use of a pre-trained and fixed domain-agnostic base network, in combination with smaller learnable domain-specific adaptation modules. In this paper, we introduce Modulation Adapters, which update the convolutional filter weights of the model in a multiplicative manner for each task. Parameterising these adaptation weights in a factored manner allows us to scale the number of per-task parameters in a flexible manner, and to strike different parameter-accuracy trade-offs. We evaluate our approach on the Visual Decathlon challenge, composed of ten image classification tasks across different domains, and on the ImageNet-to-Sketch benchmark, which consists of six image classification tasks. Our approach yields excellent results, with accuracies that are comparable to or better than those of existing state-of-the-art approaches.

Large-scale text-to-image diffusion models have significantly improved the state of the art in generative image modelling and allow for an intuitive and powerful user interface to drive the image generation process. Expressing spatial constraints, e.g. to position specific objects in particular locations, is cumbersome using text; and current text-based image generation models are not able to accurately follow such instructions. In this paper we consider image generation from text associated with segments on the image canvas, which combines an intuitive natural language interface with precise spatial control over the generated content. We propose ZestGuide, a zero-shot segmentation guidance approach that can be plugged into pre-trained text-to-image diffusion models, and does not require any additional training. It leverages implicit segmentation maps that can be extracted from cross-attention layers, and uses them to align the generation with input masks. Our experimental results combine high image quality with accurate alignment of generated content with input segmentations, and improve over prior work both quantitatively and qualitatively, including methods that require training on images with corresponding segmentations. Compared to Paint with Words, the previous state-of-the art in image generation with zero-shot segmentation conditioning, we improve by 5 to 10 mIoU points on the COCO dataset with similar FID scores.

Contrastive learning has emerged as an efficient framework to learn multimodal representations. CLIP, a seminal work in this area, achieved impressive results by training on paired image-text data using the contrastive loss. Recent work claims improvements over CLIP using additional non-contrastive losses inspired from self-supervised learning. However, it is sometimes hard to disentangle the contribution of these additional losses from other implementation details, e.g., data augmentation or regularization techniques, used to train the model. To shed light on this matter, in this paper, we first propose, implement and evaluate several baselines obtained by combining contrastive learning with recent advances in self-supervised learning. In particular, we use the loss functions that were proven successful for visual self-supervised learning to align image and text modalities. We find that these baselines outperform a basic implementation of CLIP. However, when a stronger training recipe is employed, the advantage disappears. Indeed, we find that a simple CLIP baseline can also be improved substantially, up to a 25% relative improvement on downstream zero-shot tasks, by using well-known training techniques that are popular in other subfields. Moreover, we discover that it is enough to apply image and text augmentations to make up for most of the improvement attained by prior works. With our improved training recipe for CLIP, we obtain state-of-the-art performance on four standard datasets, and consistently outperform prior work (up to +4% on the largest dataset), while being substantially simpler. The code is available at https://github.com/facebookresearch/clip-rocket, Comment: TMLR, featured certification; changelog at https://openreview.net/forum?id=a7nvXxNmdV

Recent advances in conditional generative image models have enabled impressive results. On the one hand, text-based conditional models have achieved remarkable generation quality, by leveraging large-scale datasets of image-text pairs. To enable fine-grained controllability, however, text-based models require long prompts, whose details may be ignored by the model. On the other hand, layout-based conditional models have also witnessed significant advances. These models rely on bounding boxes or segmentation maps for precise spatial conditioning in combination with coarse semantic labels. The semantic labels, however, cannot be used to express detailed appearance characteristics. In this paper, we approach fine-grained scene controllability through image collages which allow a rich visual description of the desired scene as well as the appearance and location of the objects therein, without the need of class nor attribute labels. We introduce "mixing and matching scenes" (M&Ms), an approach that consists of an adversarially trained generative image model which is conditioned on appearance features and spatial positions of the different elements in a collage, and integrates these into a coherent image. We train our model on the OpenImages (OI) dataset and evaluate it on collages derived from OI and MS-COCO datasets. Our experiments on the OI dataset show that M&Ms outperforms baselines in terms of fine-grained scene controllability while being very competitive in terms of image quality and sample diversity. On the MS-COCO dataset, we highlight the generalization ability of our model by outperforming DALL-E in terms of the zero-shot FID metric, despite using two magnitudes fewer parameters and data. Collage based generative models have the potential to advance content creation in an efficient and effective way as they are intuitive to use and yield high quality generations.

Reducing the data footprint of visual content via image compression is essential to reduce storage requirements, but also to reduce the bandwidth and latency requirements for transmission. In particular, the use of compressed images allows for faster transfer of data, and faster response times for visual recognition in edge devices that rely on cloud-based services. In this paper, we first analyze the impact of image compression using traditional codecs, as well as recent state-of-the-art neural compression approaches, on three visual recognition tasks: image classification, object detection, and semantic segmentation. We consider a wide range of compression levels, ranging from 0.1 to 2 bits-per-pixel (bpp). We find that for all three tasks, the recognition ability is significantly impacted when using strong compression. For example, for segmentation mIoU is reduced from 44.5 to 30.5 mIoU when compressing to 0.1 bpp using the best compression model we evaluated. Second, we test to what extent this performance drop can be ascribed to a loss of relevant information in the compressed image, or to a lack of generalization of visual recognition models to images with compression artefacts. We find that to a large extent the performance loss is due to the latter: by finetuning the recognition models on compressed training images, most of the performance loss is recovered. For example, bringing segmentation accuracy back up to 42 mIoU, i.e. recovering 82% of the original drop in accuracy.

Semantic image synthesis aims to generate photo realistic images given a semantic segmentation map. Despite much recent progress, training them still requires large datasets of images annotated with per-pixel label maps that are extremely tedious to obtain. To alleviate the high annotation cost, we propose a transfer method that leverages a model trained on a large source dataset to improve the learning ability on small target datasets via estimated pairwise relations between source and target classes. The class affinity matrix is introduced as a first layer to the source model to make it compatible with the target label maps, and the source model is then further finetuned for the target domain. To estimate the class affinities we consider different approaches to leverage prior knowledge: semantic segmentation on the source domain, textual label embeddings, and self-supervised vision features. We apply our approach to GAN-based and diffusion-based architectures for semantic synthesis. Our experiments show that the different ways to estimate class affinity can be effectively combined, and that our approach significantly improves over existing state-of-the-art transfer approaches for generative image models., Comment: Accepted to CVPR 2023

Data augmentation has become a crucial component to train state-of-the-art visual representation models. However, handcrafting combinations of transformations that lead to improved performances is a laborious task, which can result in visually unrealistic samples. To overcome these limitations, recent works have explored the use of generative models as learnable data augmentation tools, showing promising results in narrow application domains, e.g., few-shot learning and low-data medical imaging. In this paper, we introduce a data augmentation module, called DA_IC-GAN, which leverages instance-conditioned GAN generations and can be used off-the-shelf in conjunction with most state-of-the-art training recipes. We showcase the benefits of DA_IC-GAN by plugging it out-of-the-box into the supervised training of ResNets and DeiT models on the ImageNet dataset, and achieving accuracy boosts up to between 1%p and 2%p with the highest capacity models. Moreover, the learnt representations are shown to be more robust than the baselines when transferred to a handful of out-of-distribution datasets, and exhibit increased invariance to variations of instance and viewpoints. We additionally couple DA_IC-GAN with a self-supervised training recipe and show that we can also achieve an improvement of 1%p in accuracy in some settings. With this work, we strengthen the evidence on the potential of learnable data augmentations to improve visual representation learning, paving the road towards non-handcrafted augmentations in model training., Comment: TMLR reviews at https://openreview.net/forum?id=1n7q9mxG3T&referrer=%5BTMLR%5D(%2Fgroup%3Fid%3DTMLR)

Lossy image compression aims to represent images in as few bits as possible while maintaining fidelity to the original. Theoretical results indicate that optimizing distortion metrics such as PSNR or MS-SSIM necessarily leads to a discrepancy in the statistics of original images from those of reconstructions, in particular at low bitrates, often manifested by the blurring of the compressed images. Previous work has leveraged adversarial discriminators to improve statistical fidelity. Yet these binary discriminators adopted from generative modeling tasks may not be ideal for image compression. In this paper, we introduce a non-binary discriminator that is conditioned on quantized local image representations obtained via VQ-VAE autoencoders. Our evaluations on the CLIC2020, DIV2K and Kodak datasets show that our discriminator is more effective for jointly optimizing distortion (e.g., PSNR) and statistical fidelity (e.g., FID) than the PatchGAN of the state-of-the-art HiFiC model. On CLIC2020, we obtain the same FID as HiFiC with 30-40\% fewer bits., Comment: Upload camera-ready to arXiv. Official version available at https://proceedings.mlr.press/v202/muckley23a.html

Recent neural compression methods have been based on the popular hyperprior framework. It relies on Scalar Quantization and offers a very strong compression performance. This contrasts from recent advances in image generation and representation learning, where Vector Quantization is more commonly employed. In this work, we attempt to bring these lines of research closer by revisiting vector quantization for image compression. We build upon the VQ-VAE framework and introduce several modifications. First, we replace the vanilla vector quantizer by a product quantizer. This intermediate solution between vector and scalar quantization allows for a much wider set of rate-distortion points: It implicitly defines high-quality quantizers that would otherwise require intractably large codebooks. Second, inspired by the success of Masked Image Modeling (MIM) in the context of self-supervised learning and generative image models, we propose a novel conditional entropy model which improves entropy coding by modelling the co-dependencies of the quantized latent codes. The resulting PQ-MIM model is surprisingly effective: its compression performance on par with recent hyperprior methods. It also outperforms HiFiC in terms of FID and KID metrics when optimized with perceptual losses (e.g. adversarial). Finally, since PQ-MIM is compatible with image generation frameworks, we show qualitatively that it can operate under a hybrid mode between compression and generation, with no further training or finetuning. As a result, we explore the extreme compression regime where an image is compressed into 200 bytes, i.e., less than a tweet.

We introduce submodel co-training, a regularization method related to co-training, self-distillation and stochastic depth. Given a neural network to be trained, for each sample we implicitly instantiate two altered networks, ``submodels'', with stochastic depth: we activate only a subset of the layers. Each network serves as a soft teacher to the other, by providing a loss that complements the regular loss provided by the one-hot label. Our approach, dubbed cosub, uses a single set of weights, and does not involve a pre-trained external model or temporal averaging. Experimentally, we show that submodel co-training is effective to train backbones for recognition tasks such as image classification and semantic segmentation. Our approach is compatible with multiple architectures, including RegNet, ViT, PiT, XCiT, Swin and ConvNext. Our training strategy improves their results in comparable settings. For instance, a ViT-B pretrained with cosub on ImageNet-21k obtains 87.4% top-1 acc. @448 on ImageNet-val.

Generative image models have been extensively studied in recent years. In the unconditional setting, they model the marginal distribution from unlabelled images. To allow for more control, image synthesis can be conditioned on semantic segmentation maps that instruct the generator the position of objects in the image. While these two tasks are intimately related, they are generally studied in isolation. We propose OCO-GAN, for Optionally COnditioned GAN, which addresses both tasks in a unified manner, with a shared image synthesis network that can be conditioned either on semantic maps or directly on latents. Trained adversarially in an end-to-end approach with a shared discriminator, we are able to leverage the synergy between both tasks. We experiment with Cityscapes, COCO-Stuff, ADE20K datasets in a limited data, semi-supervised and full data regime and obtain excellent performance, improving over existing hybrid models that can generate both with and without conditioning in all settings. Moreover, our results are competitive or better than state-of-the art specialised unconditional and conditional models.

Image generation has recently seen tremendous advances, with diffusion models allowing to synthesize convincing images for a large variety of text prompts. In this article, we propose DiffEdit, a method to take advantage of text-conditioned diffusion models for the task of semantic image editing, where the goal is to edit an image based on a text query. Semantic image editing is an extension of image generation, with the additional constraint that the generated image should be as similar as possible to a given input image. Current editing methods based on diffusion models usually require to provide a mask, making the task much easier by treating it as a conditional inpainting task. In contrast, our main contribution is able to automatically generate a mask highlighting regions of the input image that need to be edited, by contrasting predictions of a diffusion model conditioned on different text prompts. Moreover, we rely on latent inference to preserve content in those regions of interest and show excellent synergies with mask-based diffusion. DiffEdit achieves state-of-the-art editing performance on ImageNet. In addition, we evaluate semantic image editing in more challenging settings, using images from the COCO dataset as well as text-based generated images., Comment: Preprint

After their initial success in natural language processing, transformer architectures have rapidly gained traction in computer vision, providing state-of-the-art results for tasks such as image classification, detection, segmentation, and video analysis. We offer three insights based on simple and easy to implement variants of vision transformers. (1) The residual layers of vision transformers, which are usually processed sequentially, can to some extent be processed efficiently in parallel without noticeably affecting the accuracy. (2) Fine-tuning the weights of the attention layers is sufficient to adapt vision transformers to a higher resolution and to other classification tasks. This saves compute, reduces the peak memory consumption at fine-tuning time, and allows sharing the majority of weights across tasks. (3) Adding MLP-based patch pre-processing layers improves Bert-like self-supervised training based on patch masking. We evaluate the impact of these design choices using the ImageNet-1k dataset, and confirm our findings on the ImageNet-v2 test set. Transfer performance is measured across six smaller datasets.

Deep generative models, like GANs, have considerably improved the state of the art in image synthesis, and are able to generate near photo-realistic images in structured domains such as human faces. Based on this success, recent work on image editing proceeds by projecting images to the GAN latent space and manipulating the latent vector. However, these approaches are limited in that only images from a narrow domain can be transformed, and with only a limited number of editing operations. We propose FlexIT, a novel method which can take any input image and a user-defined text instruction for editing. Our method achieves flexible and natural editing, pushing the limits of semantic image translation. First, FlexIT combines the input image and text into a single target point in the CLIP multimodal embedding space. Via the latent space of an auto-encoder, we iteratively transform the input image toward the target point, ensuring coherence and quality with a variety of novel regularization terms. We propose an evaluation protocol for semantic image translation, and thoroughly evaluate our method on ImageNet. Code will be made publicly available., Comment: accepted at CVPR 2022

Generative Adversarial Networks (GANs) can generate near photo realistic images in narrow domains such as human faces. Yet, modeling complex distributions of datasets such as ImageNet and COCO-Stuff remains challenging in unconditional settings. In this paper, we take inspiration from kernel density estimation techniques and introduce a non-parametric approach to modeling distributions of complex datasets. We partition the data manifold into a mixture of overlapping neighborhoods described by a datapoint and its nearest neighbors, and introduce a model, called instance-conditioned GAN (IC-GAN), which learns the distribution around each datapoint. Experimental results on ImageNet and COCO-Stuff show that IC-GAN significantly improves over unconditional models and unsupervised data partitioning baselines. Moreover, we show that IC-GAN can effortlessly transfer to datasets not seen during training by simply changing the conditioning instances, and still generate realistic images. Finally, we extend IC-GAN to the class-conditional case and show semantically controllable generation and competitive quantitative results on ImageNet; while improving over BigGAN on ImageNet-LT. Code and trained models to reproduce the reported results are available at https://github.com/facebookresearch/ic_gan., Comment: Accepted at NeurIPS2021

Following their success in natural language processing, transformers have recently shown much promise for computer vision. The self-attention operation underlying transformers yields global interactions between all tokens ,i.e. words or image patches, and enables flexible modelling of image data beyond the local interactions of convolutions. This flexibility, however, comes with a quadratic complexity in time and memory, hindering application to long sequences and high-resolution images. We propose a "transposed" version of self-attention that operates across feature channels rather than tokens, where the interactions are based on the cross-covariance matrix between keys and queries. The resulting cross-covariance attention (XCA) has linear complexity in the number of tokens, and allows efficient processing of high-resolution images. Our cross-covariance image transformer (XCiT) is built upon XCA. It combines the accuracy of conventional transformers with the scalability of convolutional architectures. We validate the effectiveness and generality of XCiT by reporting excellent results on multiple vision benchmarks, including image classification and self-supervised feature learning on ImageNet-1k, object detection and instance segmentation on COCO, and semantic segmentation on ADE20k.

We present ResMLP, an architecture built entirely upon multi-layer perceptrons for image classification. It is a simple residual network that alternates (i) a linear layer in which image patches interact, independently and identically across channels, and (ii) a two-layer feed-forward network in which channels interact independently per patch. When trained with a modern training strategy using heavy data-augmentation and optionally distillation, it attains surprisingly good accuracy/complexity trade-offs on ImageNet. We also train ResMLP models in a self-supervised setup, to further remove priors from employing a labelled dataset. Finally, by adapting our model to machine translation we achieve surprisingly good results. We share pre-trained models and our code based on the Timm library.

Convolutional networks have been extremely successful for regular data structures such as 2D images and 3D voxel grids. The transposition to meshes is, however, not straight-forward due to their irregular structure. We explore how the dual, face-based representation of triangular meshes can be leveraged as a data structure for graph convolutional networks. In the dual mesh, each node (face) has a fixed number of neighbors, which makes the networks less susceptible to overfitting on the mesh topology, and also al-lows the use of input features that are naturally defined over faces, such as surface normals and face areas. We evaluate the dual approach on the shape correspondence task on theFaust human shape dataset and variants of it with differ-ent mesh topologies. Our experiments show that results of graph convolutional networks improve when defined over the dual rather than primal mesh. Moreover, our models that explicitly leverage the neighborhood regularity of dual meshes allow improving results further while being more robust to changes in the mesh topology.

We propose a novel amortized variational inference scheme for an empirical Bayes meta-learning model, where model parameters are treated as latent variables. We learn the prior distribution over model parameters conditioned on limited training data using a variational autoencoder approach. Our framework proposes sharing the same amortized inference network between the conditional prior and variational posterior distributions over the model parameters. While the posterior leverages both the labeled support and query data, the conditional prior is based only on the labeled support data. We show that in earlier work, relying on Monte-Carlo approximation, the conditional prior collapses to a Dirac delta function. In contrast, our variational approach prevents this collapse and preserves uncertainty over the model parameters. We evaluate our approach on the miniImageNet, CIFAR-FS and FC100 datasets, and present results demonstrating its advantages over previous work., Comment: ICML 2020

Generative models have proven effective at modeling 3D shapes and their statistical variations. In this paper we investigate their application to point clouds, a 3D shape representation widely used in computer vision for which, however, only few generative models have yet been proposed. We introduce a latent variable model that builds on normalizing flows with affine coupling layers to generate 3D point clouds of an arbitrary size given a latent shape representation. To evaluate its benefits for shape modeling we apply this model for generation, autoencoding, and single-view shape reconstruction tasks. We improve over recent GAN-based models in terms of most metrics that assess generation and autoencoding. Compared to recent work based on continuous flows, our model offers a significant speedup in both training and inference times for similar or better performance. For single-view shape reconstruction we also obtain results on par with state-of-the-art voxel, point cloud, and mesh-based methods., Comment: In ECCV'20

We conduct in this work an evaluation study comparing offline and online neural machine translation architectures. Two sequence-to-sequence models: convolutional Pervasive Attention (Elbayad et al. 2018) and attention-based Transformer (Vaswani et al. 2017) are considered. We investigate, for both architectures, the impact of online decoding constraints on the translation quality through a carefully designed human evaluation on English-German and German-English language pairs, the latter being particularly sensitive to latency constraints. The evaluation results allow us to identify the strengths and shortcomings of each model when we shift to the online setup., Comment: Accepted at COLING 2020

Simultaneous machine translation consists in starting output generation before the entire input sequence is available. Wait-k decoders offer a simple but efficient approach for this problem. They first read k source tokens, after which they alternate between producing a target token and reading another source token. We investigate the behavior of wait-k decoding in low resource settings for spoken corpora using IWSLT datasets. We improve training of these models using unidirectional encoders, and training across multiple values of k. Experiments with Transformer and 2D-convolutional architectures show that our wait-k models generalize well across a wide range of latency levels. We also show that the 2D-convolution architecture is competitive with Transformers for simultaneous translation of spoken language., Comment: Accepted at INTERSPEECH 2020

Inference in deep neural networks can be computationally expensive, and networks capable of anytime inference are important in mscenarios where the amount of compute or quantity of input data varies over time. In such networks the inference process can interrupted to provide a result faster, or continued to obtain a more accurate result. We propose Hierarchical Neural Ensembles (HNE), a novel framework to embed an ensemble of multiple networks in a hierarchical tree structure, sharing intermediate layers. In HNE we control the complexity of inference on-the-fly by evaluating more or less models in the ensemble. Our second contribution is a novel hierarchical distillation method to boost the prediction accuracy of small ensembles. This approach leverages the nested structure of our ensembles, to optimally allocate accuracy and diversity across the individual models. Our experiments show that, compared to previous anytime inference models, HNE provides state-of-the-art accuracy-computate trade-offs on the CIFAR-10/100 and ImageNet datasets.

Visual localization is critical to many applications in computer vision and robotics. To address single-image RGB localization, state-of-the-art feature-based methods match local descriptors between a query image and a pre-built 3D model. Recently, deep neural networks have been exploited to regress the mapping between raw pixels and 3D coordinates in the scene, and thus the matching is implicitly performed by the forward pass through the network. However, in a large and ambiguous environment, learning such a regression task directly can be difficult for a single network. In this work, we present a new hierarchical scene coordinate network to predict pixel scene coordinates in a coarse-to-fine manner from a single RGB image. The network consists of a series of output layers, each of them conditioned on the previous ones. The final output layer predicts the 3D coordinates and the others produce progressively finer discrete location labels. The proposed method outperforms the baseline regression-only network and allows us to train compact models which scale robustly to large environments. It sets a new state-of-the-art for single-image RGB localization performance on the 7-Scenes, 12-Scenes, Cambridge Landmarks datasets, and three combined scenes. Moreover, for large-scale outdoor localization on the Aachen Day-Night dataset, we present a hybrid approach which outperforms existing scene coordinate regression methods, and reduces significantly the performance gap w.r.t. explicit feature matching methods., Comment: CVPR 2020

We study end-to-end learning strategies for 3D shape inference from images, in particular from a single image. Several approaches in this direction have been investigated that explore different shape representations and suitable learning architectures. We focus instead on the underlying probabilistic mechanisms involved and contribute a more principled probabilistic inference-based reconstruction framework, which we coin Probabilistic Reconstruction Networks. This framework expresses image conditioned 3D shape inference through a family of latent variable models, and naturally decouples the choice of shape representations from the inference itself. Moreover, it suggests different options for the image conditioning and allows training in two regimes, using either Monte Carlo or variational approximation of the marginal likelihood. Using our Probabilistic Reconstruction Networks we obtain single image 3D reconstruction results that set a new state of the art on the ShapeNet dataset in terms of the intersection over union and earth mover's distance evaluation metrics. Interestingly, we obtain these results using a basic voxel grid representation, improving over recent work based on finer point cloud or mesh based representations., Comment: Accepted as Oral at BMVC'19

Despite the outstanding performance of convolutional neural networks (CNNs) for many vision tasks, the required computational cost during inference is problematic when resources are limited. In this context, we propose Convolutional Neural Mixture Models (CNMMs), a probabilistic model embedding a large number of CNNs that can be jointly trained and evaluated in an efficient manner. Within the proposed framework, we present different mechanisms to prune subsets of CNNs from the mixture, allowing to easily adapt the computational cost required for inference. Image classification and semantic segmentation experiments show that our method achieve excellent accuracy-compute trade-offs. Moreover, unlike most of previous approaches, a single CNMM provides a large range of operating points along this trade-off, without any re-training.

Learning disentangled representations from visual data, where different high-level generative factors are independently encoded, is of importance for many computer vision tasks. Solving this problem, however, typically requires to explicitly label all the factors of interest in training images. To alleviate the annotation cost, we introduce a learning setting which we refer to as "reference-based disentangling". Given a pool of unlabeled images, the goal is to learn a representation where a set of target factors are disentangled from others. The only supervision comes from an auxiliary "reference set" containing images where the factors of interest are constant. In order to address this problem, we propose reference-based variational autoencoders, a novel deep generative model designed to exploit the weak-supervision provided by the reference set. By addressing tasks such as feature learning, conditional image generation or attribute transfer, we validate the ability of the proposed model to learn disentangled representations from this minimal form of supervision.

Unsupervised learning of generative models has seen tremendous progress over recent years, in particular due to generative adversarial networks (GANs), variational autoencoders, and flow-based models. GANs have dramatically improved sample quality, but suffer from two drawbacks: (i) they mode-drop, i.e., do not cover the full support of the train data, and (ii) they do not allow for likelihood evaluations on held-out data. In contrast, likelihood-based training encourages models to cover the full support of the train data, but yields poorer samples. These mutual shortcomings can in principle be addressed by training generative latent variable models in a hybrid adversarial-likelihood manner. However, we show that commonly made parametric assumptions create a conflict between them, making successful hybrid models non trivial. As a solution, we propose to use deep invertible transformations in the latent variable decoder. This approach allows for likelihood computations in image space, is more efficient than fully invertible models, and can take full advantage of adversarial training. We show that our model significantly improves over existing hybrid models: offering GAN-like samples, IS and FID scores that are competitive with fully adversarial models, and improved likelihood scores.

We investigate deep Bayesian neural networks with Gaussian weight priors and a class of ReLU-like nonlinearities. Bayesian neural networks with Gaussian priors are well known to induce an L2, "weight decay", regularization. Our results characterize a more intricate regularization effect at the level of the unit activations. Our main result establishes that the induced prior distribution on the units before and after activation becomes increasingly heavy-tailed with the depth of the layer. We show that first layer units are Gaussian, second layer units are sub-exponential, and units in deeper layers are characterized by sub-Weibull distributions. Our results provide new theoretical insight on deep Bayesian neural networks, which we corroborate with simulation experiments., Comment: 10 pages, 5 figures, ICML'19 conference

Image-based camera relocalization is an important problem in computer vision and robotics. Recent works utilize convolutional neural networks (CNNs) to regress for pixels in a query image their corresponding 3D world coordinates in the scene. The final pose is then solved via a RANSAC-based optimization scheme using the predicted coordinates. Usually, the CNN is trained with ground truth scene coordinates, but it has also been shown that the network can discover 3D scene geometry automatically by minimizing single-view reprojection loss. However, due to the deficiencies of the reprojection loss, the network needs to be carefully initialized. In this paper, we present a new angle-based reprojection loss, which resolves the issues of the original reprojection loss. With this new loss function, the network can be trained without careful initialization, and the system achieves more accurate results. The new loss also enables us to utilize available multi-view constraints, which further improve performance., Comment: ECCV 2018 Workshop (Geometry Meets Deep Learning)

Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on the input encoding. Both are interfaced with an attention mechanism that recombines a fixed encoding of the source tokens based on the decoder state. We propose an alternative approach which instead relies on a single 2D convolutional neural network across both sequences. Each layer of our network re-codes source tokens on the basis of the output sequence produced so far. Attention-like properties are therefore pervasive throughout the network. Our model yields excellent results, outperforming state-of-the-art encoder-decoder systems, while being conceptually simpler and having fewer parameters., Comment: Accepted at CoNLL 2018

Generative adversarial networks (GANs) are pow- erful generative models based on providing feed- back to a generative network via a discriminator network. However, the discriminator usually as- sesses individual samples. This prevents the dis- criminator from accessing global distributional statistics of generated samples, and often leads to mode dropping: the generator models only part of the target distribution. We propose to feed the discriminator with mixed batches of true and fake samples, and train it to predict the ratio of true samples in the batch. The latter score does not depend on the order of samples in a batch. Rather than learning this invariance, we introduce a generic permutation-invariant discriminator ar- chitecture. This architecture is provably a uni- versal approximator of all symmetric functions. Experimentally, our approach reduces mode col- lapse in GANs on two synthetic datasets, and obtains good results on the CIFAR10 and CelebA datasets, both qualitatively and quantitatively., Comment: Accepted at ICML 2018 (long oral)

Despite the effectiveness of recurrent neural network language models, their maximum likelihood estimation suffers from two limitations. It treats all sentences that do not match the ground truth as equally poor, ignoring the structure of the output space. Second, it suffers from "exposure bias": during training tokens are predicted given ground-truth sequences, while at test time prediction is conditioned on generated output sequences. To overcome these limitations we build upon the recent reward augmented maximum likelihood approach \ie sequence-level smoothing that encourages the model to predict sentences close to the ground truth according to a given performance metric. We extend this approach to token-level loss smoothing, and propose improvements to the sequence-level smoothing approach. Our experiments on two different tasks, image captioning and machine translation, show that token-level and sequence-level loss smoothing are complementary, and significantly improve results., Comment: Accepted by ACL 2018

Anticipating future events is an important prerequisite towards intelligent behavior. Video forecasting has been studied as a proxy task towards this goal. Recent work has shown that to predict semantic segmentation of future frames, forecasting at the semantic level is more effective than forecasting RGB frames and then segmenting these. In this paper we consider the more challenging problem of future instance segmentation, which additionally segments out individual objects. To deal with a varying number of output labels per image, we develop a predictive model in the space of fixed-sized convolutional features of the Mask R-CNN instance segmentation model. We apply the "detection head'" of Mask R-CNN on the predicted features to produce the instance segmentation of future frames. Experiments show that this approach significantly improves over strong baselines based on optical flow and repurposed instance segmentation architectures.

Generative modeling of high-dimensional data is a key problem in machine learning. Successful approaches include latent variable models and autoregressive models. The complementary strengths of these approaches, to model global and local image statistics respectively, suggest hybrid models that encode global image structure into latent variables while autoregressively modeling low level detail. Previous approaches to such hybrid models restrict the capacity of the autoregressive decoder to prevent degenerate models that ignore the latent variables and only rely on autoregressive modeling. Our contribution is a training procedure relying on an auxiliary loss function that controls which information is captured by the latent variables and what is left to the autoregressive decoder. Our approach can leverage arbitrarily powerful autoregressive decoders, achieves state-of-the art quantitative performance among models with latent variables, and generates qualitatively convincing samples., Comment: Published as a conference paper at ECML-PKDD 2018

Convolutional neural networks (CNNs) have massively impacted visual recognition in 2D images, and are now ubiquitous in state-of-the-art approaches. CNNs do not easily extend, however, to data that are not represented by regular grids, such as 3D shape meshes or other graph-structured data, to which traditional local convolution operators do not directly apply. To address this problem, we propose a novel graph-convolution operator to establish correspondences between filter weights and graph neighborhoods with arbitrary connectivity. The key novelty of our approach is that these correspondences are dynamically computed from features learned by the network, rather than relying on predefined static coordinates over the graph as in previous work. We obtain excellent experimental results that significantly improve over previous state-of-the-art shape correspondence results. This shows that our approach can learn effective shape representations from raw input coordinates, without relying on shape descriptors.

The ability to predict and therefore to anticipate the future is an important attribute of intelligence. It is also of utmost importance in real-time systems, e.g. in robotics or autonomous driving, which depend on visual scene understanding for decision making. While prediction of the raw RGB pixel values in future video frames has been studied in previous work, here we introduce the novel task of predicting semantic segmentations of future frames. Given a sequence of video frames, our goal is to predict segmentation maps of not yet observed video frames that lie up to a second or further in the future. We develop an autoregressive convolutional neural network that learns to iteratively generate multiple frames. Our results on the Cityscapes dataset show that directly predicting future segmentations is substantially better than predicting and then segmenting future RGB frames. Prediction results up to half a second in the future are visually convincing and are much more accurate than those of a baseline based on warping semantic segmentations using optical flow., Comment: Accepted to ICCV 2017. Supplementary material available on the authors' webpages

We propose "Areas of Attention", a novel attention-based model for automatic image captioning. Our approach models the dependencies between image regions, caption words, and the state of an RNN language model, using three pairwise interactions. In contrast to previous attention-based approaches that associate image regions only to the RNN state, our method allows a direct association between caption words and image regions. During training these associations are inferred from image-level captions, akin to weakly-supervised object detector training. These associations help to improve captioning by localizing the corresponding regions during testing. We also propose and compare different ways of generating attention areas: CNN activation grids, object proposals, and spatial transformers nets applied in a convolutional fashion. Spatial transformers give the best results. They allow for image specific attention areas, and can be trained jointly with the rest of the network. Our attention mechanism and spatial transformer attention areas together yield state-of-the-art results on the MSCOCO dataset.o meaningful latent semantic structure in the generated captions., Comment: Accepted in ICCV 2017

Adversarial training has been shown to produce state of the art results for generative image modeling. In this paper we propose an adversarial training approach to train semantic segmentation models. We train a convolutional semantic segmentation network along with an adversarial network that discriminates segmentation maps coming either from the ground truth or from the segmentation network. The motivation for our approach is that it can detect and correct higher-order inconsistencies between ground truth segmentation maps and the ones produced by the segmentation net. Our experiments show that our adversarial training approach leads to improved accuracy on the Stanford Background and PASCAL VOC 2012 datasets.