Robby T. Tan

Chenxin Xu, Robby T. Tan, Yuhong Tan et al. · cambridge

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.

Yeying Jin, Aashish Sharma, Robby T. Tan

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}.

Yeying Jin, Beibei Lin, Wending Yan et al.

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.

Yeying Jin, Wei Ye, Wenhan Yang et al.

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}

Yeying Jin, Ruoteng Li, Wenhan Yang et al.

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}.

Yu Cheng, Bo Wang, Robby T. Tan

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.

Xin Yang, Michael Bi Mi, Yuan Yuan et al.

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

Yeying Jin, Wenhan Yang, Robby T. Tan

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.

Yeying Jin, Wending Yan, Wenhan Yang et al.

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.

Mikhail Kennerley, Jian-Gang Wang, Bharadwaj Veeravalli et al.

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.

Wending Yan, Lu Xu, Wenhan Yang et al.

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.

Shuwei Li, Jikai Wang, Michael S. Brown et al.

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).

Aishik Nagar, Yutong Liu, Andy T. Liu et al.

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.

Yiming Chen, Xianghu Yue, Xiaoxue Gao et al.

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.

Qinqian Lei, Bo Wang, Robby T. Tan

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.

Xiao Cao, Beibei Lin, Bo Wang et al.

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.

Yiming Chen, Xianghu Yue, Chen Zhang et al.

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.

Mikhail Kennerley, Jian-Gang Wang, Bharadwaj Veeravalli et al.

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.

Xin Yang, Wending Yan, Yuan Yuan et al.

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.

Xin Zhang, Jinheng Xie, Yuan Yuan et al.

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.

Hongchao Jiang, Yiming Chen, Yushi Cao et al.

Large Language Models (LLMs) have significantly advanced the state-of-the-art in various coding tasks. Beyond directly answering user queries, LLMs can also serve as judges, assessing and comparing the quality of responses generated by other models. Such an evaluation capability is crucial both for benchmarking different LLMs and for improving response quality through response ranking. However, despite the growing adoption of the LLM-as-a-Judge paradigm, its effectiveness in coding scenarios remains underexplored due to the absence of dedicated benchmarks. To address this gap, we introduce CodeJudgeBench, a benchmark explicitly designed to evaluate the performance of LLM-as-a-Judge models across three critical coding tasks: code generation, code repair, and unit test generation. Through comprehensive benchmarking of 26 LLM-as-a-Judge models, we find that recent thinking models significantly outperform non-thinking models on our carefully designed code judging tasks. Notably, even relatively small thinking models, such as Qwen3-8B, can outperform specially trained LLM-as-a-Judge models up to 70B in size. Nevertheless, all models still exhibit significant randomness in their judgment of coding tasks. For pairwise judging tasks, simply changing the order in which responses are presented can substantially impact accuracy. In addition, when judging code and unit tests written by different LLMs, LLM-as-a-Judge models also show variance in performance. This sensitivity raises concerns about the reliability and consistency of LLM-as-a-Judge in coding scenarios. Lastly, we study optimal prompting strategies for LLM-as-a-Judge. We find that using pair-wise comparison outperforms scalar point-wise judging. Furthermore, retaining comments and reasoning in the full, unprocessed LLM response leads to improved judge performance.

Beibei Lin, Tingting Chen, Robby T. Tan

Reference-driven image completion, which restores missing regions in a target view using additional images, is particularly challenging when the target view differs significantly from the references. Existing generative methods rely solely on diffusion priors and, without geometric cues such as camera pose or depth, often produce misaligned or implausible content. We propose GeoComplete, a novel framework that incorporates explicit 3D structural guidance to enforce geometric consistency in the completed regions, setting it apart from prior image-only approaches. GeoComplete introduces two key ideas: conditioning the diffusion process on projected point clouds to infuse geometric information, and applying target-aware masking to guide the model toward relevant reference cues. The framework features a dual-branch diffusion architecture. One branch synthesizes the missing regions from the masked target, while the other extracts geometric features from the projected point cloud. Joint self-attention across branches ensures coherent and accurate completion. To address regions visible in references but absent in the target, we project the target view into each reference to detect occluded areas, which are then masked during training. This target-aware masking directs the model to focus on useful cues, enhancing performance in difficult scenarios. By integrating a geometry-aware dual-branch diffusion architecture with a target-aware masking strategy, GeoComplete offers a unified and robust solution for geometry-conditioned image completion. Experiments show that GeoComplete achieves a 17.1 PSNR improvement over state-of-the-art methods, significantly boosting geometric accuracy while maintaining high visual quality.

Yiming Chen, Chen Zhang, Danqing Luo et al.

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.

Beibei Lin, Stephen Lin, Robby Tan

Nighttime image dehazing is particularly challenging when dense haze and intense glow severely degrade or entirely obscure background information. Existing methods often struggle due to insufficient background priors and limited generative capability, both of which are highly important under such conditions. In this paper, we introduce BeyondHaze, a generative nighttime dehazing method that not only reduces haze and glow effects but also reconstructs plausible background structures in regions where visual cues are heavily degraded. Our approach is built on two main ideas: obtaining strong background priors by adapting image diffusion models to nighttime dehazing, and enhancing generative ability in haze- and glow-obscured areas through guided training. Task-specific nighttime dehazing knowledge is distilled into an image diffusion model while preserving its capacity to generate clean images. The diffusion model is further trained on tailored image pairs to improve its ability to recover background details that are suppressed by haze effects. Since generative models may introduce hallucinated content, we design our framework to allow user control over the generative level, enabling a balance between visual realism and fidelity. Experiments on real-world nighttime images demonstrate that BeyondHaze substantially improves visibility and scene detail under dense haze.

Vijay Prakash Dwivedi, Viktor Schlegel, Andy T. Liu et al.

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.

Weilong Yan, Xin Zhang, Robby T. Tan

Monocular depth estimation under adverse weather conditions (e.g.\ rain, fog, snow, and nighttime) remains highly challenging due to the lack of reliable ground truth and the difficulty of learning from unlabeled real-world data. Existing methods often rely on synthetic adverse data with pseudo-labels, which suffer from domain gaps, or employ self-supervised learning, which violates photometric assumptions in adverse scenarios. In this work, we propose to achieve weather-generalized depth estimation by Parameter-Efficient Fine-Tuning (PEFT) of Vision Foundation Models (VFMs), using only a small amount of high-visibility (normal) data. While PEFT has shown strong performance in semantic tasks such as segmentation, it remains underexplored for geometry -- centric tasks like depth estimation -- especially in terms of balancing effective adaptation with the preservation of pretrained knowledge. To this end, we introduce the Selecting-Tuning-Maintaining (STM) strategy, which structurally decomposes the pretrained weights of VFMs based on two kinds of effective ranks (entropy-rank and stable-rank). In the tuning phase, we adaptively select the proper rank number as well as the task-aware singular directions for initialization, based on the entropy-rank and full-tuned weight; while in the maintaining stage, we enforce a principal direction regularization based on the stable-rank. This design guarantees flexible task adaptation while preserving the strong generalization capability of the pretrained VFM. Extensive experiments on four real-world benchmarks across diverse weather conditions demonstrate that STM not only outperforms existing PEFT methods and full fine-tuning but also surpasses methods trained with adverse synthetic data, and even the depth foundation model

Qinqian Lei, Bo Wang, Robby T. Tan

Human-object interaction (HOI) detection has traditionally been approached with task-specific models, sometimes augmented by early vision-language models (VLMs) such as CLIP. With the rise of large, generative VLMs, however, a natural question emerges: can standalone VLMs effectively perform HOI detection, and how do they compare to specialized HOI methods? Addressing this requires a benchmarking dataset and protocol that support both paradigms. Existing benchmarks such as HICO-DET were developed before modern VLMs and rely on exact label matching. This clashes with generative outputs, which may yield multiple equally valid interpretations. For example, in a single image, a person mid-motion with a frisbee might plausibly be described as 'throwing' or 'catching', yet only one is annotated as correct. Such rigid evaluation penalizes valid predictions from both VLMs and HOI-specific methods, but disproportionately underestimates VLM performance because their outputs are less constrained. We introduce a new benchmarking dataset that reformulates HOI detection as a multiple-answer multiple-choice task. It emphasizes challenging scenarios by (i) including a higher proportion of multi-person scenes where individuals perform different interactions, (ii) removing overly simple cases, and (iii) curating hard negative choices. This makes the benchmark more challenging than prior HOI datasets, while still supporting systematic evaluation of both standalone VLMs and HOI-specific methods under a unified protocol. Our results show that large VLMs already surpass state-of-the-art HOI-specific methods across most metrics, while analysis further uncovers key limitations: VLMs often misattribute surrounding people's interactions to the target person and struggle in complex multi-person or occluded scenarios.

Mikhail Kennerley, Angelica Aviles-Rivero, Carola-Bibiane Schönlieb et al.

Combining multiple object detection datasets offers a path to improved generalisation but is hindered by inconsistencies in class semantics and bounding box annotations. Some methods to address this assume shared label taxonomies and address only spatial inconsistencies; others require manual relabelling, or produce a unified label space, which may be unsuitable when a fixed target label space is required. We propose Label-Aligned Transfer (LAT), a label transfer framework that systematically projects annotations from diverse source datasets into the label space of a target dataset. LAT begins by training dataset-specific detectors to generate pseudo-labels, which are then combined with ground-truth annotations via a Privileged Proposal Generator (PPG) that replaces the region proposal network in two-stage detectors. To further refine region features, a Semantic Feature Fusion (SFF) module injects class-aware context and features from overlapping proposals using a confidence-weighted attention mechanism. This pipeline preserves dataset-specific annotation granularity while enabling many-to-one label space transfer across heterogeneous datasets, resulting in a semantically and spatially aligned representation suitable for training a downstream detector. LAT thus jointly addresses both class-level misalignments and bounding box inconsistencies without relying on shared label spaces or manual annotations. Across multiple benchmarks, LAT demonstrates consistent improvements in target-domain detection performance, achieving gains of up to +4.8AP over semi-supervised baselines.

Yiming Chen, Simin Chen, Zexin Li et al.

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.

Yin Zhi Ng, Benjamin Choi, Robby Tan et al.

We present an approach for radar-inertial odometry which uses a continuous-time framework to fuse measurements from multiple automotive radars and an inertial measurement unit (IMU). Adverse weather conditions do not have a significant impact on the operating performance of radar sensors unlike that of camera and LiDAR sensors. Radar's robustness in such conditions and the increasing prevalence of radars on passenger vehicles motivate us to look at the use of radar for ego-motion estimation. A continuous-time trajectory representation is applied not only as a framework to enable heterogeneous and asynchronous multi-sensor fusion, but also, to facilitate efficient optimization by being able to compute poses and their derivatives in closed-form and at any given time along the trajectory. We compare our continuous-time estimates to those from a discrete-time radar-inertial odometry approach and show that our continuous-time method outperforms the discrete-time method. To the best of our knowledge, this is the first time a continuous-time framework has been applied to radar-inertial odometry.

Lu Liu, Robby T. Tan

Human-Object Interaction (HOI) detection aims to detect visual relations between human and objects in images. One significant problem of HOI detection is that non-interactive human-object pair can be easily mis-grouped and misclassified as an action, especially when humans are close and performing similar actions in the scene. To address the mis-grouping problem, we propose a spatial enhancement approach to enforce fine-level spatial constraints in two directions from human body parts to the object center, and from object parts to the human center. At inference, we propose a human-object regrouping approach by considering the object-exclusive property of an action, where the target object should not be shared by more than one human. By suppressing non-interactive pairs, our approach can decrease the false positives. Experiments on V-COCO and HICO-DET datasets demonstrate our approach is more robust compared to the existing methods under the presence of multiple humans and objects in the scene.

Cheng Yu, Bo Wang, Bo Yang et al.

Estimating 3D human poses from a monocular video is still a challenging task. Many existing methods' performance drops when the target person is occluded by other objects, or the motion is too fast/slow relative to the scale and speed of the training data. Moreover, many of these methods are not designed or trained under severe occlusion explicitly, making their performance on handling occlusion compromised. Addressing these problems, we introduce a spatio-temporal network for robust 3D human pose estimation. As humans in videos may appear in different scales and have various motion speeds, we apply multi-scale spatial features for 2D joints or keypoints prediction in each individual frame, and multi-stride temporal convolutional networks (TCNs) to estimate 3D joints or keypoints. Furthermore, we design a spatio-temporal discriminator based on body structures as well as limb motions to assess whether the predicted pose forms a valid pose and a valid movement. During training, we explicitly mask out some keypoints to simulate various occlusion cases, from minor to severe occlusion, so that our network can learn better and becomes robust to various degrees of occlusion. As there are limited 3D ground-truth data, we further utilize 2D video data to inject a semi-supervised learning capability to our network. Moreover, we observe that there is a discrepancy between 3D pose prediction and 2D pose estimation due to different pose variations between video and image training datasets. We, therefore propose a confidence-based inference stage optimization to adaptively enforce 3D pose projection to match 2D pose estimation to further improve final pose prediction accuracy. Experiments on public datasets validate the effectiveness of our method, and our ablation studies show the strengths of our network's individual submodules.

Wenhan Yang, Robby T. Tan, Shiqi Wang et al.

The goal of single-image deraining is to restore the rain-free background scenes of an image degraded by rain streaks and rain accumulation. The early single-image deraining methods employ a cost function, where various priors are developed to represent the properties of rain and background layers. Since 2017, single-image deraining methods step into a deep-learning era, and exploit various types of networks, i.e. convolutional neural networks, recurrent neural networks, generative adversarial networks, etc., demonstrating impressive performance. Given the current rapid development, in this paper, we provide a comprehensive survey of deraining methods over the last decade. We summarize the rain appearance models, and discuss two categories of deraining approaches: model-based and data-driven approaches. For the former, we organize the literature based on their basic models and priors. For the latter, we discuss developed ideas related to architectures, constraints, loss functions, and training datasets. We present milestones of single-image deraining methods, review a broad selection of previous works in different categories, and provide insights on the historical development route from the model-based to data-driven methods. We also summarize performance comparisons quantitatively and qualitatively. Beyond discussing the technicality of deraining methods, we also discuss the future directions.

Angelica I. Aviles-Rivero, Nicolas Papadakis, Ruoteng Li et al.

The task of classifying X-ray data is a problem of both theoretical and clinical interest. Whilst supervised deep learning methods rely upon huge amounts of labelled data, the critical problem of achieving a good classification accuracy when an extremely small amount of labelled data is available has yet to be tackled. In this work, we introduce a novel semi-supervised framework for X-ray classification which is based on a graph-based optimisation model. To the best of our knowledge, this is the first method that exploits graph-based semi-supervised learning for X-ray data classification. Furthermore, we introduce a new multi-class classification functional with carefully selected class priors which allows for a smooth solution that strengthens the synergy between the limited number of labels and the huge amount of unlabelled data. We demonstrate, through a set of numerical and visual experiments, that our method produces highly competitive results on the ChestX-ray14 data set whilst drastically reducing the need for annotated data.

Angelica I. Aviles-Rivero, Nicolas Papadakis, Ruoteng Li et al.

Semi-supervised classification is a great focus of interest, as in real-world scenarios obtaining labels is expensive, time-consuming and might require expert knowledge. This has motivated the fast development of semi-supervised techniques, whose performance is on a par with or better than supervised approaches. A current major challenge for semi-supervised techniques is how to better handle the network calibration and confirmation bias problems for improving performance. In this work, we argue that energy models are an effective alternative to such problems. With this motivation in mind, we propose a hybrid framework for semi-supervised classification called CREPE model (1-Lapla$\mathbf{C}$ian g$\mathbf{R}$aph $\mathbf{E}$nergy for $\mathbf{P}$seudo-lab$\mathbf{E}$ls). Firstly, we introduce a new energy model based on the non-smooth $\ell_1$ norm of the normalised graph 1-Laplacian. Our functional enforces a sufficiently smooth solution and strengthens the intrinsic relation between the labelled and unlabelled data. Secondly, we provide a theoretical analysis for our proposed scheme and show that the solution trajectory does converge to a non-constant steady point. Thirdly, we derive the connection of our energy model for pseudo-labelling. We show that our energy model produces more meaningful pseudo-labels than the ones generated directly by a deep network. We extensively evaluate our framework, through numerical and visual experiments, using six benchmarking datasets for natural and medical images. We demonstrate that our technique reports state-of-the-art results for semi-supervised classification.

Lu Liu, Robby T. Tan

One of the successful approaches in semi-supervised learning is based on the consistency regularization. Typically, a student model is trained to be consistent with teacher prediction for the inputs under different perturbations. To be successful, the prediction targets given by teacher should have good quality, otherwise the student can be misled by teacher. Unfortunately, existing methods do not assess the quality of the teacher targets. In this paper, we propose a novel Certainty-driven Consistency Loss (CCL) that exploits the predictive uncertainty in the consistency loss to let the student dynamically learn from reliable targets. Specifically, we propose two approaches, i.e. Filtering CCL and Temperature CCL to either filter out uncertain predictions or pay less attention on them in the consistency regularization. We further introduce a novel decoupled framework to encourage model difference. Experimental results on SVHN, CIFAR-10, and CIFAR-100 demonstrate the advantages of our method over a few existing methods.

Lu Liu, Robby T. Tan, Shaodi You

One significant problem of deep-learning based human action recognition is that it can be easily misled by the presence of irrelevant objects or backgrounds. Existing methods commonly address this problem by employing bounding boxes on the target humans as part of the input, in both training and testing stages. This requirement of bounding boxes as part of the input is needed to enable the methods to ignore irrelevant contexts and extract only human features. However, we consider this solution is inefficient, since the bounding boxes might not be available. Hence, instead of using a person bounding box as an input, we introduce a human-mask loss to automatically guide the activations of the feature maps to the target human who is performing the action, and hence suppress the activations of misleading contexts. We propose a multi-task deep learning method that jointly predicts the human action class and human location heatmap. Extensive experiments demonstrate our approach is more robust compared to the baseline methods under the presence of irrelevant misleading contexts. Our method achieves 94.06\% and 40.65\% (in terms of mAP) on Stanford40 and MPII dataset respectively, which are 3.14\% and 12.6\% relative improvements over the best results reported in the literature, and thus set new state-of-the-art results. Additionally, unlike some existing methods, we eliminate the requirement of using a person bounding box as an input during testing.

Yu Li, Shaodi You, Michael S. Brown et al.

This paper provides a comprehensive survey of methods dealing with visibility enhancement of images taken in hazy or foggy scenes. The survey begins with discussing the optical models of atmospheric scattering media and image formation. This is followed by a survey of existing methods, which are grouped to multiple image methods, polarizing filters based methods, methods with known depth, and single-image methods. We also provide a benchmark of a number of well known single-image methods, based on a recent dataset provided by Fattal and our newly generated scattering media dataset that contains ground truth images for quantitative evaluation. To our knowledge, this is the first benchmark using numerical metrics to evaluate dehazing techniques. This benchmark allows us to objectively compare the results of existing methods and to better identify the strengths and limitations of each method.

Jiaolong Yang, Hongdong Li, Yuchao Dai et al.

This paper deals with a challenging, frequently encountered, yet not properly investigated problem in two-frame optical flow estimation. That is, the input frames are compounds of two imaging layers -- one desired background layer of the scene, and one distracting, possibly moving layer due to transparency or reflection. In this situation, the conventional brightness constancy constraint -- the cornerstone of most existing optical flow methods -- will no longer be valid. In this paper, we propose a robust solution to this problem. The proposed method performs both optical flow estimation, and image layer separation. It exploits a generalized double-layer brightness consistency constraint connecting these two tasks, and utilizes the priors for both of them. Experiments on both synthetic data and real images have confirmed the efficacy of the proposed method. To the best of our knowledge, this is the first attempt towards handling generic optical flow fields of two-frame images containing transparency or reflection.

Shaodi You, Robby T. Tan, Rei Kawakami et al.

This paper introduces depth estimation from water drops. The key idea is that a single water drop adhered to window glass is totally transparent and convex, and thus optically acts like a fisheye lens. If we have more than one water drop in a single image, then through each of them we can see the environment with different view points, similar to stereo. To realize this idea, we need to rectify every water drop imagery to make radially distorted planar surfaces look flat. For this rectification, we consider two physical properties of water drops: (1) A static water drop has constant volume, and its geometric convex shape is determined by the balance between the tension force and gravity. This implies that the 3D geometric shape can be obtained by minimizing the overall potential energy, which is the sum of the tension energy and the gravitational potential energy. (2) The imagery inside a water-drop is determined by the water-drop 3D shape and total reflection at the boundary. This total reflection generates a dark band commonly observed in any adherent water drops. Hence, once the 3D shape of water drops are recovered, we can rectify the water drop images through backward raytracing. Subsequently, we can compute depth using stereo. In addition to depth estimation, we can also apply image refocusing. Experiments on real images and a quantitative evaluation show the effectiveness of our proposed method. To our best knowledge, never before have adherent water drops been used to estimate depth.