Search

Detecting Human-Object Interactions (HOI) in zero-shot settings, where models must handle unseen classes, poses significant challenges. Existing methods that rely on aligning visual encoders with large Vision-Language Models (VLMs) to tap into the extensive knowledge of VLMs, require large, computationally expensive models and encounter training difficulties. Adapting VLMs with prompt learning offers an alternative to direct alignment. However, fine-tuning on task-specific datasets often leads to overfitting to seen classes and suboptimal performance on unseen classes, due to the absence of unseen class labels. To address these challenges, we introduce a novel prompt learning-based framework for Efficient Zero-Shot HOI detection (EZ-HOI). First, we introduce Large Language Model (LLM) and VLM guidance for learnable prompts, integrating detailed HOI descriptions and visual semantics to adapt VLMs to HOI tasks. However, because training datasets contain seen-class labels alone, fine-tuning VLMs on such datasets tends to optimize learnable prompts for seen classes instead of unseen ones. Therefore, we design prompt learning for unseen classes using information from related seen classes, with LLMs utilized to highlight the differences between unseen and related seen classes. Quantitative evaluations on benchmark datasets demonstrate that our EZ-HOI achieves state-of-the-art performance across various zero-shot settings with only 10.35% to 33.95% of the trainable parameters compared to existing methods. Code is available at https://github.com/ChelsieLei/EZ-HOI., Comment: Accepted by NeurIPS 2024

Building on the success of large language models (LLMs), recent advancements such as GPT-4o have enabled real-time speech interactions through LLM-based voice assistants, offering a significantly improved user experience compared to traditional text-based interactions. However, the absence of benchmarks designed to evaluate these speech interaction capabilities has hindered progress of LLM-based voice assistants development. Current evaluations focus primarily on automatic speech recognition (ASR) or general knowledge evaluation with clean speeches, neglecting the more intricate, real-world scenarios that involve diverse speaker characteristics, environmental and content factors. To address this, we introduce VoiceBench, the first benchmark designed to provide a multi-faceted evaluation of LLM-based voice assistants. VoiceBench also includes both real and synthetic spoken instructions that incorporate the above three key real-world variations. Extensive experiments reveal the limitations of current LLM-based voice assistant models and offer valuable insights for future research and development in this field., Comment: Work in progress. Data is available at https://github.com/MatthewCYM/VoiceBench

Large Language Models (LLMs) have demonstrated remarkable performance across various domains, including healthcare. However, their ability to effectively represent structured non-textual data, such as the alphanumeric medical codes used in records like ICD-10 or SNOMED-CT, is limited and has been particularly exposed in recent research. This paper examines the challenges LLMs face in processing medical codes due to the shortcomings of current tokenization methods. As a result, we introduce the UniStruct architecture to design a multimodal medical foundation model of unstructured text and structured data, which addresses these challenges by adapting subword tokenization techniques specifically for the structured medical codes. Our approach is validated through model pre-training on both an extensive internal medical database and a public repository of structured medical records. Trained on over 1 billion tokens on the internal medical database, the proposed model achieves up to a 23% improvement in evaluation metrics, with around 2% gain attributed to our proposed tokenization. Additionally, when evaluated on the EHRSHOT public benchmark with a 1/1000 fraction of the pre-training data, the UniStruct model improves performance on over 42% of the downstream tasks. Our approach not only enhances the representation and generalization capabilities of patient-centric models but also bridges a critical gap in representation learning models' ability to handle complex structured medical data, alongside unstructured text., Comment: NeurIPS 2024 Workshop on Unifying Representations in Neural Models (UniReps 2024)

The perennial demand for highly efficient short-haul communications is evidenced by a sustained explosion of growth in data center infrastructure that is predicted to continue for the foreseeable future. In these relatively compact networks, cost-sensitivity is of particular importance, which limits options to direct detection schemes that are more cost efficient than their coherent counterparts. Since their initial demonstration, multi-soliton states in optical microresonators have been observed to manifest in self-organised ensembles where soliton pulses are equally spaced around the resonators. In the spectral domain, these states, dubbed soliton crystals (SCs), result in significant enhancements to individual comb lines depending on the crystal state, making them well suited towards intensity-modulated direct detection (IMDD) schemes. In this work, we experimentally demonstrate adiabatic, deterministic access to lower-order soliton crystal states using an auxiliary-assisted cavity pumping method, attaining up to 19.6 dB enhancement of the comb lines in the 7-SC configuration compared to the single-soliton state. Seven comb lines of each 46 Gbaud/s pulse amplitude modulation 4 (PAM4) is transmitted over 4km of fiber in comb lines across the C-band with bit-error-rates (BER) as low as 5E-5. Our demonstration shows the promising way of using soliton crystal states as future integrated sources for highly stable Terabaud/s datacenter communications.

Two dimensional (2D) crystals have attracted strong interest as a new class of proton conducting materials that can block atoms, molecules and ions while allowing proton transport through the atomically thin basal planes. Although 2D materials exhibit this perfect selectivity, the reported proton conductivities have been relatively low. Here we show that vacancy-rich titania monolayers are highly permeable to protons while remaining impermeable to helium with proton conductivity exceeding 100 S cm-2 at 200 C and surpassing targets set by industry roadmaps. The fast and selective proton transport is attributed to an extremely high density of titanium-atom vacancies (one per square nm), which effectively turns titania monolayers into angstrom-scale sieves. Our findings highlight the potential of 2D oxides as membrane materials for hydrogen-based technologies.

Various audio-LLMs (ALLMs) have been explored recently for tackling different audio tasks simultaneously using a single, unified model. While existing evaluations of ALLMs primarily focus on single-audio tasks, real-world applications often involve processing multiple audio streams simultaneously. To bridge this gap, we propose the first multi-audio evaluation (MAE) benchmark that consists of 20 datasets from 11 multi-audio tasks encompassing both speech and sound scenarios. Comprehensive experiments on MAE demonstrate that the existing ALLMs, while being powerful in comprehending primary audio elements in individual audio inputs, struggling to handle multi-audio scenarios. To this end, we propose a novel multi-audio-LLM (MALLM) to capture audio context among multiple similar audios using discriminative learning on our proposed synthetic data. The results demonstrate that the proposed MALLM outperforms all baselines and achieves high data efficiency using synthetic data without requiring human annotations. The proposed MALLM opens the door for ALLMs towards multi-audio processing era and brings us closer to replicating human auditory capabilities in machines., Comment: EMNLP24 Findings. Data available at https://github.com/MatthewCYM/MALLM

Transmitting an entangled state over an extended distance is crucial for the development of quantum networks. Previous demonstrations of transmitting entangled photons over long distance using satellites or fibers have use entangled photon pairs generated from bulk crystal arrangements. An alternative approach would be to generate photon pairs using silicon-on-insulator (SOI) chips. Despite numerous proof-of-concept studies, no long range distribution has been achieved using this platform because of the challenge of getting sufficient off-chip brightness. We report a SOI platform that provides an off-chip entangled photon pair brightness of between 8,000 to 460,000 pairs per second. This exceeds previous reports by three orders of magnitude in brightness. The entanglement fidelity is 99.85(6)% and 97.90(3)% respectively. Measuring one photon locally, and transmitting the other over 93 km of deployed fiber (link loss of 40 dB), achieves a count rate of 132 pairs per second with an entanglement fidelity of 93.3(3)%, after solving the additional challenges of chromatic dispersion. The source can be pumped harder to enable transmission of entangled photons over 155 km of deployed fiber (link loss of 66 dB) at a rate of 0.7 pairs per second, with an entanglement fidelity of 87.6(5)%. These results demonstrate that SOI nanophotonic chips can perform competitively with bulk crystal sources and represent an important step toward building quantum networks using integrated nanophotonic platforms.

Medical abstractive summarization faces the challenge of balancing faithfulness and informativeness. Current methods often sacrifice key information for faithfulness or introduce confabulations when prioritizing informativeness. While recent advancements in techniques like in-context learning (ICL) and fine-tuning have improved medical summarization, they often overlook crucial aspects such as faithfulness and informativeness without considering advanced methods like model reasoning and self-improvement. Moreover, the field lacks a unified benchmark, hindering systematic evaluation due to varied metrics and datasets. This paper addresses these gaps by presenting a comprehensive benchmark of six advanced abstractive summarization methods across three diverse datasets using five standardized metrics. Building on these findings, we propose uMedSum, a modular hybrid summarization framework that introduces novel approaches for sequential confabulation removal followed by key missing information addition, ensuring both faithfulness and informativeness. Our work improves upon previous GPT-4-based state-of-the-art (SOTA) medical summarization methods, significantly outperforming them in both quantitative metrics and qualitative domain expert evaluations. Notably, we achieve an average relative performance improvement of 11.8% in reference-free metrics over the previous SOTA. Doctors prefer uMedSum's summaries 6 times more than previous SOTA in difficult cases where there are chances of confabulations or missing information. These results highlight uMedSum's effectiveness and generalizability across various datasets and metrics, marking a significant advancement in medical summarization., Comment: 12 pages

Sparse view NeRF is challenging because limited input images lead to an under constrained optimization problem for volume rendering. Existing methods address this issue by relying on supplementary information, such as depth maps. However, generating this supplementary information accurately remains problematic and often leads to NeRF producing images with undesired artifacts. To address these artifacts and enhance robustness, we propose SSNeRF, a sparse view semi supervised NeRF method based on a teacher student framework. Our key idea is to challenge the NeRF module with progressively severe sparse view degradation while providing high confidence pseudo labels. This approach helps the NeRF model become aware of noise and incomplete information associated with sparse views, thus improving its robustness. The novelty of SSNeRF lies in its sparse view specific augmentations and semi supervised learning mechanism. In this approach, the teacher NeRF generates novel views along with confidence scores, while the student NeRF, perturbed by the augmented input, learns from the high confidence pseudo labels. Our sparse view degradation augmentation progressively injects noise into volume rendering weights, perturbs feature maps in vulnerable layers, and simulates sparse view blurriness. These augmentation strategies force the student NeRF to recognize degradation and produce clearer rendered views. By transferring the student's parameters to the teacher, the teacher gains increased robustness in subsequent training iterations. Extensive experiments demonstrate the effectiveness of our SSNeRF in generating novel views with less sparse view degradation. We will release code upon acceptance.

Existing 2D human pose estimation research predominantly concentrates on well-lit scenarios, with limited exploration of poor lighting conditions, which are a prevalent aspect of daily life. Recent studies on low-light pose estimation require the use of paired well-lit and low-light images with ground truths for training, which are impractical due to the inherent challenges associated with annotation on low-light images. To this end, we introduce a novel approach that eliminates the need for low-light ground truths. Our primary novelty lies in leveraging two complementary-teacher networks to generate more reliable pseudo labels, enabling our model achieves competitive performance on extremely low-light images without the need for training with low-light ground truths. Our framework consists of two stages. In the first stage, our model is trained on well-lit data with low-light augmentations. In the second stage, we propose a dual-teacher framework to utilize the unlabeled low-light data, where a center-based main teacher produces the pseudo labels for relatively visible cases, while a keypoints-based complementary teacher focuses on producing the pseudo labels for the missed persons of the main teacher. With the pseudo labels from both teachers, we propose a person-specific low-light augmentation to challenge a student model in training to outperform the teachers. Experimental results on real low-light dataset (ExLPose-OCN) show, our method achieves 6.8% (2.4 AP) improvement over the state-of-the-art (SOTA) method, despite no low-light ground-truth data is used in our approach, in contrast to the SOTA method. Our code will be available at:https://github.com/ayh015-dev/DA-LLPose., Comment: 18 pages, 3 figure. Accepted by ECCV24

A fundamental challenge in endoscopy is how to fabricate a small fiber-optic probe that can achieve comparable function to probes with large, complicated optics (e.g., high resolution and extended depth of focus). To achieve high resolution over an extended depth of focus (DOF), the application of needle-like beams has been proposed. However, existing methods using miniaturized needle beam designs fail to adequately correct astigmatism and other monochromatic aberrations, limiting the resolution of at least one axis. Here, we describe a novel approach to realize freeform beam-shaping endoscopic probes via two-photon direct laser writing, also known as micro 3D-printing. We present a design achieving approximately 8-micron resolution with a DOF of >0.8 mm at a central wavelength of 1310 nm. The probe has a diameter of 0.25 mm (without the catheter sheaths) and is fabricated using a single printing step directly on the optical fiber. We demonstrate our device in intravascular imaging of living atherosclerotic pigs at multiple time points, as well as human arteries with plaques ex vivo. This is the first step to enable beam-tailoring endoscopic probes which achieve diffraction-limited resolution over a large DOF.

The automatic evaluation of natural language generation (NLG) systems presents a long-lasting challenge. Recent studies have highlighted various neural metrics that align well with human evaluations. Yet, the robustness of these evaluators against adversarial perturbations remains largely under-explored due to the unique challenges in obtaining adversarial data for different NLG evaluation tasks. To address the problem, we introduce AdvEval, a novel black-box adversarial framework against NLG evaluators. AdvEval is specially tailored to generate data that yield strong disagreements between human and victim evaluators. Specifically, inspired by the recent success of large language models (LLMs) in text generation and evaluation, we adopt strong LLMs as both the data generator and gold evaluator. Adversarial data are automatically optimized with feedback from the gold and victim evaluator. We conduct experiments on 12 victim evaluators and 11 NLG datasets, spanning tasks including dialogue, summarization, and question evaluation. The results show that AdvEval can lead to significant performance degradation of various victim metrics, thereby validating its efficacy., Comment: ACL24 Findings

Domain adaptive object detection aims to adapt detection models to domains where annotated data is unavailable. Existing methods have been proposed to address the domain gap using the semi-supervised student-teacher framework. However, a fundamental issue arises from the class imbalance in the labelled training set, which can result in inaccurate pseudo-labels. The relationship between classes, especially where one class is a majority and the other minority, has a large impact on class bias. We propose Class-Aware Teacher (CAT) to address the class bias issue in the domain adaptation setting. In our work, we approximate the class relationships with our Inter-Class Relation module (ICRm) and exploit it to reduce the bias within the model. In this way, we are able to apply augmentations to highly related classes, both inter- and intra-domain, to boost the performance of minority classes while having minimal impact on majority classes. We further reduce the bias by implementing a class-relation weight to our classification loss. Experiments conducted on various datasets and ablation studies show that our method is able to address the class bias in the domain adaptation setting. On the Cityscapes to Foggy Cityscapes dataset, we attained a 52.5 mAP, a substantial improvement over the 51.2 mAP achieved by the state-of-the-art method., Comment: Accepted into CVPR 2024

Masked autoencoder (MAE) shows that severe augmentation during training produces robust representations for high-level tasks. This paper brings the MAE-like framework to nighttime image enhancement, demonstrating that severe augmentation during training produces strong network priors that are resilient to real-world night haze degradations. We propose a novel nighttime image dehazing method with self-prior learning. Our main novelty lies in the design of severe augmentation, which allows our model to learn robust priors. Unlike MAE that uses masking, we leverage two key challenging factors of nighttime images as augmentation: light effects and noise. During training, we intentionally degrade clear images by blending them with light effects as well as by adding noise, and subsequently restore the clear images. This enables our model to learn clear background priors. By increasing the noise values to approach as high as the pixel intensity values of the glow and light effect blended images, our augmentation becomes severe, resulting in stronger priors. While our self-prior learning is considerably effective in suppressing glow and revealing details of background scenes, in some cases, there are still some undesired artifacts that remain, particularly in the forms of over-suppression. To address these artifacts, we propose a self-refinement module based on the semi-supervised teacher-student framework. Our NightHaze, especially our MAE-like self-prior learning, shows that models trained with severe augmentation effectively improve the visibility of input haze images, approaching the clarity of clear nighttime images. Extensive experiments demonstrate that our NightHaze achieves state-of-the-art performance, outperforming existing nighttime image dehazing methods by a substantial margin of 15.5% for MUSIQ and 23.5% for ClipIQA.

Semantic segmentation's performance is often compromised when applied to unlabeled adverse weather conditions. Unsupervised domain adaptation is a potential approach to enhancing the model's adaptability and robustness to adverse weather. However, existing methods encounter difficulties when sequentially adapting the model to multiple unlabeled adverse weather conditions. They struggle to acquire new knowledge while also retaining previously learned knowledge.To address these problems, we propose a semantic segmentation method for multiple adverse weather conditions that incorporates adaptive knowledge acquisition, pseudolabel blending, and weather composition replay. Our adaptive knowledge acquisition enables the model to avoid learning from extreme images that could potentially cause the model to forget. In our approach of blending pseudo-labels, we not only utilize the current model but also integrate the previously learned model into the ongoing learning process. This collaboration between the current teacher and the previous model enhances the robustness of the pseudo-labels for the current target. Our weather composition replay mechanism allows the model to continuously refine its previously learned weather information while simultaneously learning from the new target domain. Our method consistently outperforms the stateof-the-art methods, and obtains the best performance with averaged mIoU (%) of 65.7 and the lowest forgetting (%) of 3.6 against 60.1 and 11.3, on the ACDC datasets for a four-target continual multi-target domain adaptation.

Unsupervised object discovery and localization aims to detect or segment objects in an image without any supervision. Recent efforts have demonstrated a notable potential to identify salient foreground objects by utilizing self-supervised transformer features. However, their scopes only build upon patch-level features within an image, neglecting region/image-level and cross-image relationships at a broader scale. Moreover, these methods cannot differentiate various semantics from multiple instances. To address these problems, we introduce Hierarchical mErging framework via contrAstive grouPing (HEAP). Specifically, a novel lightweight head with cross-attention mechanism is designed to adaptively group intra-image patches into semantically coherent regions based on correlation among self-supervised features. Further, to ensure the distinguishability among various regions, we introduce a region-level contrastive clustering loss to pull closer similar regions across images. Also, an image-level contrastive loss is present to push foreground and background representations apart, with which foreground objects and background are accordingly discovered. HEAP facilitates efficient hierarchical image decomposition, which contributes to more accurate object discovery while also enabling differentiation among objects of various classes. Extensive experimental results on semantic segmentation retrieval, unsupervised object discovery, and saliency detection tasks demonstrate that HEAP achieves state-of-the-art performance., Comment: Accepted by AAAI24

We report a stable, low loss method for coupling light from silicon-on-insulator (SOI) photonic chips into optical fibers. The technique is realized using an on-chip tapered waveguide and a cleaved small core optical fiber. The on-chip taper is monolithic and does not require a patterned cladding, thus simplifying the chip fabrication process. The optical fiber segment is composed of a centimeter-long small core fiber (UHNA7) which is spliced to SMF-28 fiber with less than -0.1 dB loss. We observe an overall coupling loss of -0.64 dB with this design. The chip edge and fiber tip can be butt coupled without damaging the on-chip taper or fiber. Friction between the surfaces maintains alignment leading to an observation of +-0.1 dB coupling fluctuation during a ten-day continuous measurement without use of any adhesive. This technique minimizes the potential for generating Raman noise in the fiber, and has good stability compared to coupling strategies based on longer UHNA fibers or fragile lensed fibers. We also applied the edge coupler on a correlated photon pair source and observed a raw coincidence count rate of 1.21 million cps and raw heralding efficiency of 21.3%. We achieved an auto correlation function g^(2) (0) as low as 0.0004 at the low pump power regime.

Detecting human-object interactions (HOI) in a few-shot setting remains a challenge. Existing meta-learning methods struggle to extract representative features for classification due to the limited data, while existing few-shot HOI models rely on HOI text labels for classification. Moreover, some query images may display visual similarity to those outside their class, such as similar backgrounds between different HOI classes. This makes learning more challenging, especially with limited samples. Bongard-HOI (Jiang et al. 2022) epitomizes this HOI few-shot problem, making it the benchmark we focus on in this paper. In our proposed method, we introduce novel label-uncertain query augmentation techniques to enhance the diversity of the query inputs, aiming to distinguish the positive HOI class from the negative ones. As these augmented inputs may or may not have the same class label as the original inputs, their class label is unknown. Those belonging to a different class become hard samples due to their visual similarity to the original ones. Additionally, we introduce a novel pseudo-label generation technique that enables a mean teacher model to learn from the augmented label-uncertain inputs. We propose to augment the negative support set for the student model to enrich the semantic information, fostering diversity that challenges and enhances the student's learning. Experimental results demonstrate that our method sets a new state-of-the-art (SOTA) performance by achieving 68.74% accuracy on the Bongard-HOI benchmark, a significant improvement over the existing SOTA of 66.59%. In our evaluation on HICO-FS, a more general few-shot recognition dataset, our method achieves 73.27% accuracy, outperforming the previous SOTA of 71.20% in the 5-way 5-shot task., Comment: 9 pages, 4 figures

In 3D human shape and pose estimation from a monocular video, models trained with limited labeled data cannot generalize well to videos with occlusion, which is common in the wild videos. The recent human neural rendering approaches focusing on novel view synthesis initialized by the off-the-shelf human shape and pose methods have the potential to correct the initial human shape. However, the existing methods have some drawbacks such as, erroneous in handling occlusion, sensitive to inaccurate human segmentation, and ineffective loss computation due to the non-regularized opacity field. To address these problems, we introduce ORTexME, an occlusion-robust temporal method that utilizes temporal information from the input video to better regularize the occluded body parts. While our ORTexME is based on NeRF, to determine the reliable regions for the NeRF ray sampling, we utilize our novel average texture learning approach to learn the average appearance of a person, and to infer a mask based on the average texture. In addition, to guide the opacity-field updates in NeRF to suppress blur and noise, we propose the use of human body mesh. The quantitative evaluation demonstrates that our method achieves significant improvement on the challenging multi-person 3DPW dataset, where our method achieves 1.8 P-MPJPE error reduction. The SOTA rendering-based methods fail and enlarge the error up to 5.6 on the same dataset., Comment: 8 pages, 8 figures

Exploring spatial-temporal dependencies from observed motions is one of the core challenges of human motion prediction. Previous methods mainly focus on dedicated network structures to model the spatial and temporal dependencies. This paper considers a new direction by introducing a model learning framework with auxiliary tasks. In our auxiliary tasks, partial body joints' coordinates are corrupted by either masking or adding noise and the goal is to recover corrupted coordinates depending on the rest coordinates. To work with auxiliary tasks, we propose a novel auxiliary-adapted transformer, which can handle incomplete, corrupted motion data and achieve coordinate recovery via capturing spatial-temporal dependencies. Through auxiliary tasks, the auxiliary-adapted transformer is promoted to capture more comprehensive spatial-temporal dependencies among body joints' coordinates, leading to better feature learning. Extensive experimental results have shown that our method outperforms state-of-the-art methods by remarkable margins of 7.2%, 3.7%, and 9.4% in terms of 3D mean per joint position error (MPJPE) on the Human3.6M, CMU Mocap, and 3DPW datasets, respectively. We also demonstrate that our method is more robust under data missing cases and noisy data cases. Code is available at https://github.com/MediaBrain-SJTU/AuxFormer., Comment: Accpeted to ICCV2023

Visibility in hazy nighttime scenes is frequently reduced by multiple factors, including low light, intense glow, light scattering, and the presence of multicolored light sources. Existing nighttime dehazing methods often struggle with handling glow or low-light conditions, resulting in either excessively dark visuals or unsuppressed glow outputs. In this paper, we enhance the visibility from a single nighttime haze image by suppressing glow and enhancing low-light regions. To handle glow effects, our framework learns from the rendered glow pairs. Specifically, a light source aware network is proposed to detect light sources of night images, followed by the APSF (Atmospheric Point Spread Function)-guided glow rendering. Our framework is then trained on the rendered images, resulting in glow suppression. Moreover, we utilize gradient-adaptive convolution, to capture edges and textures in hazy scenes. By leveraging extracted edges and textures, we enhance the contrast of the scene without losing important structural details. To boost low-light intensity, our network learns an attention map, then adjusted by gamma correction. This attention has high values on low-light regions and low values on haze and glow regions. Extensive evaluation on real nighttime haze images, demonstrates the effectiveness of our method. Our experiments demonstrate that our method achieves a PSNR of 30.38dB, outperforming state-of-the-art methods by 13% on GTA5 nighttime haze dataset. Our data and code is available at https://github.com/jinyeying/nighttime_dehaze., Comment: Accepted to ACM'MM2023, https://github.com/jinyeying/nighttime_dehaze

Despite much success in natural language processing (NLP), pre-trained language models typically lead to a high computational cost during inference. Multi-exit is a mainstream approach to address this issue by making a trade-off between efficiency and accuracy, where the saving of computation comes from an early exit. However, whether such saving from early-exiting is robust remains unknown. Motivated by this, we first show that directly adapting existing adversarial attack approaches targeting model accuracy cannot significantly reduce inference efficiency. To this end, we propose a simple yet effective attacking framework, SAME, a novel slowdown attack framework on multi-exit models, which is specially tailored to reduce the efficiency of the multi-exit models. By leveraging the multi-exit models' design characteristics, we utilize all internal predictions to guide the adversarial sample generation instead of merely considering the final prediction. Experiments on the GLUE benchmark show that SAME can effectively diminish the efficiency gain of various multi-exit models by 80% on average, convincingly validating its effectiveness and generalization ability., Comment: Accepted by ACL2023

Sensitivity to severe occlusion and large view angles limits the usage scenarios of the existing monocular 3D dense face alignment methods. The state-of-the-art 3DMM-based method, directly regresses the model's coefficients, underutilizing the low-level 2D spatial and semantic information, which can actually offer cues for face shape and orientation. In this work, we demonstrate how modeling 3D facial geometry in image and model space jointly can solve the occlusion and view angle problems. Instead of predicting the whole face directly, we regress image space features in the visible facial region by dense prediction first. Subsequently, we predict our model's coefficients based on the regressed feature of the visible regions, leveraging the prior knowledge of whole face geometry from the morphable models to complete the invisible regions. We further propose a fusion network that combines the advantages of both the image and model space predictions to achieve high robustness and accuracy in unconstrained scenarios. Thanks to the proposed fusion module, our method is robust not only to occlusion and large pitch and roll view angles, which is the benefit of our image space approach, but also to noise and large yaw angles, which is the benefit of our model space method. Comprehensive evaluations demonstrate the superior performance of our method compared with the state-of-the-art methods. On the 3D dense face alignment task, we achieve 3.80% NME on the AFLW2000-3D dataset, which outperforms the state-of-the-art method by 5.5%. Code is available at https://github.com/lhyfst/DSFNet., Comment: Accepted into CVPR'23

Talking face generation, also known as speech-to-lip generation, reconstructs facial motions concerning lips given coherent speech input. The previous studies revealed the importance of lip-speech synchronization and visual quality. Despite much progress, they hardly focus on the content of lip movements i.e., the visual intelligibility of the spoken words, which is an important aspect of generation quality. To address the problem, we propose using a lip-reading expert to improve the intelligibility of the generated lip regions by penalizing the incorrect generation results. Moreover, to compensate for data scarcity, we train the lip-reading expert in an audio-visual self-supervised manner. With a lip-reading expert, we propose a novel contrastive learning to enhance lip-speech synchronization, and a transformer to encode audio synchronically with video, while considering global temporal dependency of audio. For evaluation, we propose a new strategy with two different lip-reading experts to measure intelligibility of the generated videos. Rigorous experiments show that our proposal is superior to other State-of-the-art (SOTA) methods, such as Wav2Lip, in reading intelligibility i.e., over 38% Word Error Rate (WER) on LRS2 dataset and 27.8% accuracy on LRW dataset. We also achieve the SOTA performance in lip-speech synchronization and comparable performances in visual quality., Comment: accepted by CVPR 2023

Object detection at night is a challenging problem due to the absence of night image annotations. Despite several domain adaptation methods, achieving high-precision results remains an issue. False-positive error propagation is still observed in methods using the well-established student-teacher framework, particularly for small-scale and low-light objects. This paper proposes a two-phase consistency unsupervised domain adaptation network, 2PCNet, to address these issues. The network employs high-confidence bounding-box predictions from the teacher in the first phase and appends them to the student's region proposals for the teacher to re-evaluate in the second phase, resulting in a combination of high and low confidence pseudo-labels. The night images and pseudo-labels are scaled-down before being used as input to the student, providing stronger small-scale pseudo-labels. To address errors that arise from low-light regions and other night-related attributes in images, we propose a night-specific augmentation pipeline called NightAug. This pipeline involves applying random augmentations, such as glare, blur, and noise, to daytime images. Experiments on publicly available datasets demonstrate that our method achieves superior results to state-of-the-art methods by 20\%, and to supervised models trained directly on the target data., Comment: Accepted into CVPR'23

Learning to predict agent motions with relationship reasoning is important for many applications. In motion prediction tasks, maintaining motion equivariance under Euclidean geometric transformations and invariance of agent interaction is a critical and fundamental principle. However, such equivariance and invariance properties are overlooked by most existing methods. To fill this gap, we propose EqMotion, an efficient equivariant motion prediction model with invariant interaction reasoning. To achieve motion equivariance, we propose an equivariant geometric feature learning module to learn a Euclidean transformable feature through dedicated designs of equivariant operations. To reason agent's interactions, we propose an invariant interaction reasoning module to achieve a more stable interaction modeling. To further promote more comprehensive motion features, we propose an invariant pattern feature learning module to learn an invariant pattern feature, which cooperates with the equivariant geometric feature to enhance network expressiveness. We conduct experiments for the proposed model on four distinct scenarios: particle dynamics, molecule dynamics, human skeleton motion prediction and pedestrian trajectory prediction. Experimental results show that our method is not only generally applicable, but also achieves state-of-the-art prediction performances on all the four tasks, improving by 24.0/30.1/8.6/9.2%. Code is available at https://github.com/MediaBrain-SJTU/EqMotion., Comment: Accepted to CVPR 2023

Estimating the reflectance layer from a single image is a challenging task. It becomes more challenging when the input image contains shadows or specular highlights, which often render an inaccurate estimate of the reflectance layer. Therefore, we propose a two-stage learning method, including reflectance guidance and a Shadow/Specular-Aware (S-Aware) network to tackle the problem. In the first stage, an initial reflectance layer free from shadows and specularities is obtained with the constraint of novel losses that are guided by prior-based shadow-free and specular-free images. To further enforce the reflectance layer to be independent of shadows and specularities in the second-stage refinement, we introduce an S-Aware network that distinguishes the reflectance image from the input image. Our network employs a classifier to categorize shadow/shadow-free, specular/specular-free classes, enabling the activation features to function as attention maps that focus on shadow/specular regions. Our quantitative and qualitative evaluations show that our method outperforms the state-of-the-art methods in the reflectance layer estimation that is free from shadows and specularities. Code is at: \url{https://github.com/jinyeying/S-Aware-network}., Comment: Accepted to AAAI2023, https://github.com/jinyeying/S-Aware-network

Most existing domain adaptation (DA) methods align the features based on the domain feature distributions and ignore aspects related to fog, background and target objects, rendering suboptimal performance. In our DA framework, we retain the depth and background information during the domain feature alignment. A consistency loss between the generated depth and fog transmission map is introduced to strengthen the retention of the depth information in the aligned features. To address false object features potentially generated during the DA process, we propose an encoder-decoder framework to reconstruct the fog-free background image. This reconstruction loss also reinforces the encoder, i.e., our DA backbone, to minimize false object features.Moreover, we involve our target data in training both our DA module and our detection module in a semi-supervised manner, so that our detection module is also exposed to the unlabeled target data, the type of data used in the testing stage. Using these ideas, our method significantly outperforms the state-of-the-art method (47.6 mAP against the 44.3 mAP on the Foggy Cityscapes dataset), and obtains the best performance on multiple real-image public datasets. Code is available at: https://github.com/VIML-CVDL/Object-Detection-in-Foggy-Scenes, Comment: Accepted by ACCV

The assumption of a uniform light color distribution is no longer applicable in scenes that have multiple light colors. Most color constancy methods are designed to deal with a single light color, and thus are erroneous when applied to multiple light colors. The spatial variability in multiple light colors causes the color constancy problem to be more challenging and requires the extraction of local surface/light information. Motivated by this, we introduce a multi-task learning method to discount multiple light colors in a single input image. To have better cues of the local surface/light colors under multiple light color conditions, we design a novel multi-task learning framework. Our framework includes auxiliary tasks of achromatic-pixel detection and surface-color similarity prediction, providing better cues for local light and surface colors, respectively. Moreover, to ensure that our model maintains the constancy of surface colors regardless of the variations of light colors, a novel local surface color feature preservation scheme is developed. We demonstrate that our model achieves 47.1% improvement (from 4.69 mean angular error to 2.48) compared to a state-of-the-art multi-illuminant color constancy method on a multi-illuminant dataset (LSMI)., Comment: 8 pages, 6 figures

Removing soft and self shadows that lack clear boundaries from a single image is still challenging. Self shadows are shadows that are cast on the object itself. Most existing methods rely on binary shadow masks, without considering the ambiguous boundaries of soft and self shadows. In this paper, we present DeS3, a method that removes hard, soft and self shadows based on adaptive attention and ViT similarity. Our novel ViT similarity loss utilizes features extracted from a pre-trained Vision Transformer. This loss helps guide the reverse sampling towards recovering scene structures. Our adaptive attention is able to differentiate shadow regions from the underlying objects, as well as shadow regions from the object casting the shadow. This capability enables DeS3 to better recover the structures of objects even when they are partially occluded by shadows. Different from existing methods that rely on constraints during the training phase, we incorporate the ViT similarity during the sampling stage. Our method outperforms state-of-the-art methods on the SRD, AISTD, LRSS, USR and UIUC datasets, removing hard, soft, and self shadows robustly. Specifically, our method outperforms the SOTA method by 16\% of the RMSE of the whole image on the LRSS dataset. Our data and code is available at: \url{https://github.com/jinyeying/DeS3_Deshadow}, Comment: Accepted to AAAI2024, diffusion shadow removal, \url{https://github.com/jinyeying/DeS3_Deshadow}

Few existing image defogging or dehazing methods consider dense and non-uniform particle distributions, which usually happen in smoke, dust and fog. Dealing with these dense and/or non-uniform distributions can be intractable, since fog's attenuation and airlight (or veiling effect) significantly weaken the background scene information in the input image. To address this problem, we introduce a structure-representation network with uncertainty feedback learning. Specifically, we extract the feature representations from a pre-trained Vision Transformer (DINO-ViT) module to recover the background information. To guide our network to focus on non-uniform fog areas, and then remove the fog accordingly, we introduce the uncertainty feedback learning, which produces the uncertainty maps, that have higher uncertainty in denser fog regions, and can be regarded as an attention map that represents fog's density and uneven distribution. Based on the uncertainty map, our feedback network refines our defogged output iteratively. Moreover, to handle the intractability of estimating the atmospheric light colors, we exploit the grayscale version of our input image, since it is less affected by varying light colors that are possibly present in the input image. The experimental results demonstrate the effectiveness of our method both quantitatively and qualitatively compared to the state-of-the-art methods in handling dense and non-uniform fog or smoke., Comment: Accepted to ACCV2022, data in https://github.com/jinyeying/FogRemoval

In multi-person 2D pose estimation, the bottom-up methods simultaneously predict poses for all persons, and unlike the top-down methods, do not rely on human detection. However, the SOTA bottom-up methods' accuracy is still inferior compared to the existing top-down methods. This is due to the predicted human poses being regressed based on the inconsistent human bounding box center and the lack of human-scale normalization, leading to the predicted human poses being inaccurate and small-scale persons being missed. To push the envelope of the bottom-up pose estimation, we firstly propose multi-scale training to enhance the network to handle scale variation with single-scale testing, particularly for small-scale persons. Secondly, we introduce dual anatomical centers (i.e., head and body), where we can predict the human poses more accurately and reliably, especially for small-scale persons. Moreover, existing bottom-up methods use multi-scale testing to boost the accuracy of pose estimation at the price of multiple additional forward passes, which weakens the efficiency of bottom-up methods, the core strength compared to top-down methods. By contrast, our multi-scale training enables the model to predict high-quality poses in a single forward pass (i.e., single-scale testing). Our method achieves 38.4\% improvement on bounding box precision and 39.1\% improvement on bounding box recall over the state of the art (SOTA) on the challenging small-scale persons subset of COCO. For the human pose AP evaluation, we achieve a new SOTA (71.0 AP) on the COCO test-dev set with the single-scale testing. We also achieve the top performance (40.3 AP) on OCHuman dataset in cross-dataset evaluation., Comment: 28 pages, 10 figures, and 6 tables

Night images suffer not only from low light, but also from uneven distributions of light. Most existing night visibility enhancement methods focus mainly on enhancing low-light regions. This inevitably leads to over enhancement and saturation in bright regions, such as those regions affected by light effects (glare, floodlight, etc). To address this problem, we need to suppress the light effects in bright regions while, at the same time, boosting the intensity of dark regions. With this idea in mind, we introduce an unsupervised method that integrates a layer decomposition network and a light-effects suppression network. Given a single night image as input, our decomposition network learns to decompose shading, reflectance and light-effects layers, guided by unsupervised layer-specific prior losses. Our light-effects suppression network further suppresses the light effects and, at the same time, enhances the illumination in dark regions. This light-effects suppression network exploits the estimated light-effects layer as the guidance to focus on the light-effects regions. To recover the background details and reduce hallucination/artefacts, we propose structure and high-frequency consistency losses. Our quantitative and qualitative evaluations on real images show that our method outperforms state-of-the-art methods in suppressing night light effects and boosting the intensity of dark regions., Comment: Accepted to ECCV2022

Shadow removal from a single image is generally still an open problem. Most existing learning-based methods use supervised learning and require a large number of paired images (shadow and corresponding non-shadow images) for training. A recent unsupervised method, Mask-ShadowGAN~\cite{Hu19}, addresses this limitation. However, it requires a binary mask to represent shadow regions, making it inapplicable to soft shadows. To address the problem, in this paper, we propose an unsupervised domain-classifier guided shadow removal network, DC-ShadowNet. Specifically, we propose to integrate a shadow/shadow-free domain classifier into a generator and its discriminator, enabling them to focus on shadow regions. To train our network, we introduce novel losses based on physics-based shadow-free chromaticity, shadow-robust perceptual features, and boundary smoothness. Moreover, we show that our unsupervised network can be used for test-time training that further improves the results. Our experiments show that all these novel components allow our method to handle soft shadows, and also to perform better on hard shadows both quantitatively and qualitatively than the existing state-of-the-art shadow removal methods. Our code is available at: \url{https://github.com/jinyeying/DC-ShadowNet-Hard-and-Soft-Shadow-Removal}., Comment: Accepted to ICCV2021, https://github.com/jinyeying/DC-ShadowNet-Hard-and-Soft-Shadow-Removal

Existing adherent raindrop removal methods focus on the detection of the raindrop locations, and then use inpainting techniques or generative networks to recover the background behind raindrops. Yet, as adherent raindrops are diverse in sizes and appearances, the detection is challenging for both single image and video. Moreover, unlike rain streaks, adherent raindrops tend to cover the same area in several frames. Addressing these problems, our method employs a two-stage video-based raindrop removal method. The first stage is the single image module, which generates initial clean results. The second stage is the multiple frame module, which further refines the initial results using temporal constraints, namely, by utilizing multiple input frames in our process and applying temporal consistency between adjacent output frames. Our single image module employs a raindrop removal network to generate initial raindrop removal results, and create a mask representing the differences between the input and initial output. Once the masks and initial results for consecutive frames are obtained, our multiple-frame module aligns the frames in both the image and feature levels and then obtains the clean background. Our method initially employs optical flow to align the frames, and then utilizes deformable convolution layers further to achieve feature-level frame alignment. To remove small raindrops and recover correct backgrounds, a target frame is predicted from adjacent frames. A series of unsupervised losses are proposed so that our second stage, which is the video raindrop removal module, can self-learn from video data without ground truths. Experimental results on real videos demonstrate the state-of-art performance of our method both quantitatively and qualitatively.

Monocular 3D human pose estimation has made progress in recent years. Most of the methods focus on single persons, which estimate the poses in the person-centric coordinates, i.e., the coordinates based on the center of the target person. Hence, these methods are inapplicable for multi-person 3D pose estimation, where the absolute coordinates (e.g., the camera coordinates) are required. Moreover, multi-person pose estimation is more challenging than single pose estimation, due to inter-person occlusion and close human interactions. Existing top-down multi-person methods rely on human detection (i.e., top-down approach), and thus suffer from the detection errors and cannot produce reliable pose estimation in multi-person scenes. Meanwhile, existing bottom-up methods that do not use human detection are not affected by detection errors, but since they process all persons in a scene at once, they are prone to errors, particularly for persons in small scales. To address all these challenges, we propose the integration of top-down and bottom-up approaches to exploit their strengths. Our top-down network estimates human joints from all persons instead of one in an image patch, making it robust to possible erroneous bounding boxes. Our bottom-up network incorporates human-detection based normalized heatmaps, allowing the network to be more robust in handling scale variations. Finally, the estimated 3D poses from the top-down and bottom-up networks are fed into our integration network for final 3D poses. To address the common gaps between training and testing data, we do optimization during the test time, by refining the estimated 3D human poses using high-order temporal constraint, re-projection loss, and bone length regularizations. Our evaluations demonstrate the effectiveness of the proposed method. Code and models are available: https://github.com/3dpose/3D-Multi-Person-Pose., Comment: Accepted by TPAMI 2022. arXiv admin note: substantial text overlap with arXiv:2104.01797

Simulating complex molecules and materials is an anticipated application of quantum devices. With strong quantum advantage demonstrated in artificial tasks, we examine how such advantage translates into modeling physical problems of correlated electronic structure. We simulate static and dynamical electronic structure on a superconducting quantum processor derived from Google's Sycamore architecture for two representative correlated electron problems: the nitrogenase iron-sulfur molecular clusters, and $\alpha$-ruthenium trichloride, a proximate spin-liquid material. To do so, we simplify the electronic structure into low-energy spin models that fit on the device. With extensive error mitigation and assistance from classically simulated data, we achieve quantitatively meaningful results deploying about 1/5 of the gate resources used in artificial quantum advantage experiments on a similar architecture. This increases to over 1/2 of the gate resources when choosing a model that suits the hardware. Our work serves to convert artificial measures of quantum advantage into a physically relevant setting., Comment: 17 pages, 5 figures