论文检索

Yiyuan Pan, Yunzhe Xu, Zhe Liu, Hesheng Wang

Humans navigate unfamiliar environments using episodic simulation and episodic memory, which facilitate a deeper understanding of the complex relationships between environments and objects. Developing an imaginative memory system inspired by human mechanisms can enhance the navigation performance of embodied agents in unseen environments. However, existing Vision-and-Language Navigation (VLN) agents lack a memory mechanism of this kind. To address this, we propose a novel architecture that equips agents with a reality-imagination hybrid memory system. This system enables agents to maintain and expand their memory through both imaginative mechanisms and navigation actions. Additionally, we design tailored pre-training tasks to develop the agent's imaginative capabilities. Our agent can imagine high-fidelity RGB images for future scenes, achieving state-of-the-art results in a Success rate weighted by Path Length (SPL).

Yimu Pan, Sitao Zhang, Alison D. Gernand, Jeffery A. Goldstein, James Z. Wang

Robustness and generalizability in medical image segmentation are often hindered by scarcity and limited diversity of training data, which stands in contrast to the variability encountered during inference. While conventional strategies---such as domain-specific augmentation, specialized architectures, and tailored training procedures---can alleviate these issues, they depend on the availability and reliability of domain knowledge. When such knowledge is unavailable, misleading, or improperly applied, performance may deteriorate. In response, we introduce a novel, domain-agnostic, add-on, and data-driven strategy inspired by image stacking in image denoising. Termed ``semantic stacking,'' our method estimates a denoised semantic representation that complements the conventional segmentation loss during training. This method does not depend on domain-specific assumptions, making it broadly applicable across diverse image modalities, model architectures, and augmentation techniques. Through extensive experiments, we validate the superiority of our approach in improving segmentation performance under diverse conditions.

Xiaotian Pan, Zhaobo Qi, Xin Sun, Yuanrong Xu, Weigang Zhang

Procedure planning in instructional videos, producing a structured and plannable action sequence facilitating the transition from the start to the goal states, has achieved significant progress. The dominant single-branch non-autoregressive planning paradigm guides action sequence generation through action labels, overlooking the limitation of the absence of intermediate visual information. Hence, we introduce the procedure knowledge decoupled distillation strategy to address the above issue. This innovative strategy deliberately lets the teacher model see the real visual information among the start and goal states to enhance its action semantic understanding and relationship modeling ability, producing the potential probability distribution containing the real action class and other action classes that may occur. Accordingly, we introduce a decoupled intermediate information knowledge distillation loss, which comprises single action knowledge distillation and sequence distribution knowledge distillation for the student model. The former improves the student model's precise inference ability for individual actions by transferring knowledge of a single action target category using binary classification loss. Conversely, the latter uses MSE loss to constrain the student model to learn the action sequence probability distribution from the teacher model, thereby enhancing the student model's global planning capability. Extensive experiments on three datasets demonstrate that our strategy can improve the performance of multiple weakly supervised models, achieving promising procedure knowledge modeling ability and plug-and-play flexibility.

Wenjie Pan, Jianqing Zhu, Huanqiang Zeng

There are two manifestations of classification fairness. One is the preference for head classes with more instances due to the long-tail (LT) distribution of training data. The other is the clever Hans (CH) effect, where non-discriminative features are mistakenly used for classification. In this paper, we find that using category-agnostic zero-valued data can simultaneously reveal both types of unfairness. Based on this, we propose a zero uniformity training (ZUT) framework to optimize classification fairness. The ZUT framework inputs category-agnostic zero-valued data into the model in parallel and uses zero uniformity loss (ZUL) to optimize classification fairness. The ZUL loss mitigates bias towards specific classes by unifying the classification features corresponding to zero-valued data. The ZUT framework is compatible with various classification-based tasks. Experiments show that the ZUT framework can improve the performance of multiple state-of-the-art methods in image classification, person re-identification, and semantic segmentation.

Shaoyan Pan, Yikang Liu, Lin Zhao, Eric Z. Chen, Xiao Chen, Terrence Chen, Shanhui Sun

The accurate segmentation of guidewires in interventional cardiac fluoroscopy videos is crucial for computer-aided navigation tasks. Although deep learning methods have demonstrated high accuracy and robustness in wire segmentation, they require substantial annotated datasets for generalizability, underscoring the need for extensive labeled data to enhance model performance. To address this challenge, we propose the Segmentation-guided Frame-consistency Video Diffusion Model (SF-VD) to generate large collections of labeled fluoroscopy videos, augmenting the training data for wire segmentation networks. SF-VD leverages videos with limited annotations by independently modeling scene distribution and motion distribution. It first samples the scene distribution by generating 2D fluoroscopy images with wires positioned according to a specified input mask, and then samples the motion distribution by progressively generating subsequent frames, ensuring frame-to-frame coherence through a frame-consistency strategy. A segmentation-guided mechanism further refines the process by adjusting wire contrast, ensuring a diverse range of visibility in the synthesized image. Evaluation on a fluoroscopy dataset confirms the superior quality of the generated videos and shows significant improvements in guidewire segmentation.

Qingtao Pan, Wenhao Qiao, Jingjiao Lou, Bing Ji, Shuo Li

Semi-supervised medical image segmentation (SSMIS) uses consistency learning to regularize model training, which alleviates the burden of pixel-wise manual annotations. However, it often suffers from error supervision from low-quality pseudo labels. Vision-Language Model (VLM) has great potential to enhance pseudo labels by introducing text prompt guided multimodal supervision information. It nevertheless faces the cross-modal problem: the obtained messages tend to correspond to multiple targets. To address aforementioned problems, we propose a Dual Semantic Similarity-Supervised VLM (DuSSS) for SSMIS. Specifically, 1) a Dual Contrastive Learning (DCL) is designed to improve cross-modal semantic consistency by capturing intrinsic representations within each modality and semantic correlations across modalities. 2) To encourage the learning of multiple semantic correspondences, a Semantic Similarity-Supervision strategy (SSS) is proposed and injected into each contrastive learning process in DCL, supervising semantic similarity via the distribution-based uncertainty levels. Furthermore, a novel VLM-based SSMIS network is designed to compensate for the quality deficiencies of pseudo-labels. It utilizes the pretrained VLM to generate text prompt guided supervision information, refining the pseudo label for better consistency regularization. Experimental results demonstrate that our DuSSS achieves outstanding performance with Dice of 82.52%, 74.61% and 78.03% on three public datasets (QaTa-COV19, BM-Seg and MoNuSeg).

Linchao Pan, Can Gao, Jie Zhou, Jinbao Wang

Learning with Noisy Labels (LNL) aims to improve the model generalization when facing data with noisy labels, and existing methods generally assume that noisy labels come from known classes, called closed-set noise. However, in real-world scenarios, noisy labels from similar unknown classes, i.e., open-set noise, may occur during the training and inference stage. Such open-world noisy labels may significantly impact the performance of LNL methods. In this study, we propose a novel dual-space joint learning method to robustly handle the open-world noise. To mitigate model overfitting on closed-set and open-set noises, a dual representation space is constructed by two networks. One is a projection network that learns shared representations in the prototype space, while the other is a One-Vs-All (OVA) network that makes predictions using unique semantic representations in the class-independent space. Then, bi-level contrastive learning and consistency regularization are introduced in two spaces to enhance the detection capability for data with unknown classes. To benefit from the memorization effects across different types of samples, class-independent margin criteria are designed for sample identification, which selects clean samples, weights closed-set noise, and filters open-set noise effectively. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods and achieves an average accuracy improvement of 4.55\% and an AUROC improvement of 6.17\% on CIFAR80N.

Jiancheng Pan, Yanxing Liu, Yuqian Fu, Muyuan Ma, Jiahao Li, Danda Pani Paudel, Luc Van Gool, Xiaomeng Huang

Object detection, particularly open-vocabulary object detection, plays a crucial role in Earth sciences, such as environmental monitoring, natural disaster assessment, and land-use planning. However, existing open-vocabulary detectors, primarily trained on natural-world images, struggle to generalize to remote sensing images due to a significant data domain gap. Thus, this paper aims to advance the development of open-vocabulary object detection in remote sensing community. To achieve this, we first reformulate the task as Locate Anything on Earth (LAE) with the goal of detecting any novel concepts on Earth. We then developed the LAE-Label Engine which collects, auto-annotates, and unifies up to 10 remote sensing datasets creating the LAE-1M — the first large-scale remote sensing object detection dataset with broad category coverage. Using the LAE-1M, we further propose and train the novel LAE-DINO Model, the first open-vocabulary foundation object detector for the LAE task, featuring Dynamic Vocabulary Construction (DVC) and Visual-Guided Text Prompt Learning (VisGT) modules. DVC dynamically constructs vocabulary for each training batch, while VisGT maps visual features to semantic space, enhancing text features. We comprehensively conduct experiments on established remote sensing benchmark DIOR, DOTAv2.0, as well as our newly introduced 80-class LAE-80C benchmark. Results demonstrate the advantages of the LAE-1M dataset and the effectiveness of the LAE-DINO method.

Delin Pan, Jiansong Fan, Jie Zhu, Llihua Li, Xiang Pan

Federated Semi-Supervised Learning (FSSL) has emerged as a crucial topic in medical image analysis, allowing multiple medical institutions to collaboratively train a global model using limited labeled data. However, existing FSSL methods focus solely on an effective combination of federated learning and semi-supervised learning, ignoring the heterogeneity of client data and the inadaptability of semi-supervised methods in diverse environments, which leads to knowledge bias in local models and impedes stable convergence. To this end, we explore the application of personalization in FSSL and propose a novel dual-calibrated co-training framework. To adapt to the unique feature distribution of client data, we consider collaborative relationships among clients to aggregate a personalized model for each client. We further build a dual-student architecture with the personalized model and private local model on the client side, which encourages model disagreement for co-training while enhancing participant privacy. Most importantly, we design dual calibration strategies that adaptively optimize the model: Local calibration improves the boundary discrimination of the local model by dynamically replacing pseudo-label boundary patches; Global calibration corrects model direction based on the real-time perception of the biases between local dual-student models. Experimental results show the effectiveness of our method on a private medical dataset and two public medical datasets.

Chao Pan, Yu Wu, Ke Tang, Qing Li, Xin Yao

The study of enhancing model robustness against adversarial examples has become increasingly critical in the security of deep learning, leading to the development of numerous adversarial defense techniques. While these defense methods have shown promise in mitigating the impact of adversarial perturbations, evaluating their effectiveness remains a critical challenge. The recently introduced AutoAttack technique has been recognized as a standardized method for assessing model robustness. However, the computational demands of the AutoAttack method significantly limits its applicability, underscoring the urgent need for efficient evaluation techniques. To address this challenge, we propose a novel and efficient evaluation framework based on strategic constraint relaxation. Our key insight is that temporarily expanding the adversarial perturbation bounds during the attack process can help discover more effective adversarial examples. Based on this insight, we develop the Constraint Relaxation Attack (CR Attack) method, which systematically relaxes and resets perturbation constraints during optimization. Extensive experiments on 105 robust models show that CR Attack outperforms AutoAttack in both attack success rate and efficiency, reducing forward and backward propagation time by 38.3× and 15.9× respectively. Through comprehensive analysis, we validate that the constraint relaxation mechanism is crucial for the method's effectiveness.

Hongwei Niu, Jie Hu, Jianghang Lin, Guannan Jiang, Shengchuan Zhang

Open-vocabulary panoptic segmentation aims to segment and classify everything in diverse scenes across an unbounded vocabulary. Existing methods typically employ two-stage or single-stage framework. The two-stage framework involves cropping the image multiple times using masks generated by a mask generator, followed by feature extraction, while the single-stage framework relies on a heavyweight mask decoder to make up for the lack of spatial position information through self-attention and cross-attention in multiple stacked Transformer blocks. Both methods incur substantial computational overhead, thereby hindering the efficiency of model inference. To fill the gap in efficiency, we propose EOV-Seg, a novel single-stage, shared, efficient, and spatialaware framework designed for open-vocabulary panoptic segmentation. Specifically, EOV-Seg innovates in two aspects. First, a Vocabulary-Aware Selection (VAS) module is proposed to improve the semantic comprehension of visual aggregated features and alleviate the feature interaction burden on the mask decoder. Second, we introduce a Two-way Dynamic Embedding Experts (TDEE), which efficiently utilizes the spatial awareness capabilities of ViT-based CLIP backbone. To the best of our knowledge, EOV-Seg is the first open-vocabulary panoptic segmentation framework towards efficiency, which runs faster and achieves competitive performance compared with state-of-the-art methods. Specifically, with COCO training only, EOV-Seg achieves 24.5 PQ, 32.1 mIoU, and 11.6 FPS on the ADE20K dataset and the inference time of EOV-Seg is 4-19 times faster than state-of-the-art methods. Especially, equipped with ResNet50 backbone, EOV-Seg runs 23.8 FPS with only 71M parameters on a single RTX 3090 GPU.

Hongwei Niu, Linhuang Xie, Jianghang Lin, Shengchuan Zhang

Domain Generalized Semantic Segmentation (DGSS) seeks to utilize source domain data exclusively to enhance the generalization of semantic segmentation across unknown target domains. Prevailing studies predominantly concentrate on feature normalization and domain randomization, these approaches exhibit significant limitations. Feature normalization-based methods tend to confuse semantic features in the process of constraining the feature space distribution, resulting in classification misjudgment. Domain randomization-based methods frequently incorporate domain-irrelevant noise due to the uncontrollability of style transformations, resulting in segmentation ambiguity. To address these challenges, we introduce a novel framework, named SCSD for Semantic Consistency prediction and Style Diversity generalization. It comprises three pivotal components: Firstly, a Semantic Query Booster is designed to enhance the semantic awareness and discrimination capabilities of object queries in the mask decoder, enabling cross-domain semantic consistency prediction. Secondly, we develop a Text-Driven Style Transform module that utilizes domain difference text embeddings to controllably guide the style transformation of image features, thereby increasing inter-domain style diversity. Lastly, to prevent the collapse of similar domain feature spaces, we introduce a Style Synergy Optimization mechanism that fortifies the separation of inter-domain features and the aggregation of intra-domain features by synergistically weighting style contrastive loss and style aggregation loss. Extensive experiments demonstrate that the proposed SCSD significantly outperforms existing state-of-theart methods. Notably, SCSD trained on GTAV achieved an average of 49.11 mIoU on the four unseen domain datasets, surpassing the state-of-the-art method by +4.08 mIoU.

Ziming Nie, Qiao Wu, Chenlei Lv, Siwen Quan, Zhaoshuai Qi, Muze Wang, Jiaqi Yang

Point cloud upsampling aims to generate dense and uniformly distributed point sets from sparse point clouds. Existing point cloud upsampling methods typically approach the task as an interpolation problem. They achieve upsampling by performing local interpolation between point clouds or in the feature space, then regressing the interpolated points to appropriate positions. By contrast, our proposed method treats point cloud upsampling as a global shape completion problem. Specifically, our method first divides the point cloud into multiple patches. Then a masking operation is applied to remove some patches, leaving visible point cloud patches. Finally, our custom-designed neural network iterative completes the missing sections of the point cloud through the visible parts. During testing, by selecting different mask sequences, we can restore various complete patches. A sufficiently dense upsampled point cloud can be obtained by merging all the completed patches. We demonstrate the superior performance of our method through both quantitative and qualitative experiments, showing overall superiority against both existing self-supervised and supervised methods.

Thong Thanh Nguyen, Yi Bin, Xiaobao Wu, Zhiyuan Hu, Cong-Duy T Nguyen, See-Kiong Ng, Anh Tuan Luu

Temporal grounding, which localizes video moments related to a natural language query, is a core problem of vision-language learning and video understanding. To encode video moments of varying lengths, recent methods employ a multi-level structure known as a feature pyramid. In this structure, lower levels concentrate on short-range video moments, while higher levels address long-range moments. Because higher levels experience downsampling to accommodate increasing moment length, their capacity to capture information is reduced and consequently leads to degraded information in moment representations. To resolve this problem, we propose a contrastive learning framework to capture salient semantics among video moments. Our key methodology is to leverage samples from the feature space emanating from multiple stages of the video encoder itself requiring neither data augmentation nor online memory banks to obtain positive and negative samples. To enable such an extension, we introduce a sampling process to draw multiple video moments corresponding to a common query. Subsequently, by utilizing these moments' representations across video encoder layers, we instantiate a novel form of multi-scale and cross-scale contrastive learning that links local short-range video moments with global long-range video moments. Extensive experiments demonstrate the effectiveness of our framework for not only long-form but also short-form video grounding.

Thong Thanh Nguyen, Xiaobao Wu, Yi Bin, Cong-Duy T Nguyen, See-Kiong Ng, Anh Tuan Luu

To equip artificial intelligence with a comprehensive understanding towards a temporal world, video and 4D panoptic scene graph generation abstracts visual data into nodes to represent entities and edges to capture temporal relations. Existing methods encode entity masks tracked across temporal dimensions (mask tubes), then predict their relations with temporal pooling operation, which does not fully utilize the motion indicative of the entities' relation. To overcome this limitation, we introduce a contrastive representation learning framework that focuses on motion pattern for temporal scene graph generation. Firstly, our framework encourages the model to learn close representations for mask tubes of similar subject-relation-object triplets. Secondly, we seek to push apart mask tubes from their temporally shuffled versions. Moreover, we also learn distant representations for mask tubes belonging to the same video but different triplets. Extensive experiments show that our motion-aware contrastive framework significantly improves state-of-the-art methods on both video and 4D datasets.

Son Minh Nguyen, Duc Viet Le, Paul Havinga

We propose iMoT, an innovative Transformer-based inertial odometry method that retrieves cross-modal information from motion and rotation modalities for accurate positional estimation. Unlike prior work, during the encoding of the motion context, we introduce Progressive Series Decoupler at the beginning of each encoder layer to stand out critical motion events inherent in acceleration and angular velocity signals. To better aggregate cross-modal interactions, we present Adaptive Positional Encoding, which dynamically modifies positional embeddings for temporal discrepancies between different modalities. During decoding, we introduce a small set of learnable query motion particles as priors to model motion uncertainties within velocity segments. Each query motion particle is intended to draw cross-modal features dedicated to a specific motion mode, all taken together allowing the model to refine its understanding of motion dynamics effectively. Lastly, we design a dynamic scoring mechanism to stabilize iMoT's optimization by considering all aligned motion particles at the final decoding step, ensuring robust and accurate velocity segment estimation. Extensive evaluations on various inertial datasets demonstrate that iMoT significantly outperforms state-of-the-art methods in delivering superior robustness and accuracy in trajectory reconstruction.

Hung Nguyen, Quang Qui-Vinh Nguyen, Khoi Nguyen, Rang Nguyen

Given an input video of a person and a new garment, the objective of this paper is to synthesize a new video where the person is wearing the specified garment while maintaining spatiotemporal consistency. Although significant advances have been made in image-based virtual try-on, extending these successes to video often leads to frame-to-frame inconsistencies. Some approaches have attempted to address this by increasing the overlap of frames across multiple video chunks, but this comes at a steep computational cost due to the repeated processing of the same frames, especially for long video sequences. To tackle these challenges, we reconceptualize video virtual try-on as a conditional video inpainting task, with garments serving as input conditions. Specifically, our approach enhances image diffusion models by incorporating temporal attention layers to improve temporal coherence. To reduce computational overhead, we propose ShiftCaching, a novel technique that maintains temporal consistency while minimizing redundant computations. Furthermore, we introduce the TikTokDress dataset, a new video try-on dataset featuring more complex backgrounds, challenging movements, and higher resolution compared to existing public datasets. Extensive experiments demonstrate that our approach outperforms current baselines, particularly in terms of video consistency and inference speed.

Ba Hung Ngo, Doanh C. Bui, Nhat-Tuong Do-Tran, Tae Jong Choi

The enhanced representational power and broad applicability of deep learning models have attracted significant interest from the research community in recent years. However, these models often struggle to perform effectively under domain shift conditions, where the training data (the source domain) is related to but exhibits different distributions from the testing data (the target domain). To address this challenge, previous studies have attempted to reduce the domain gap between source and target data by incorporating a few labeled target samples during training—a technique known as semi-supervised domain adaptation (SSDA). While this strategy has demonstrated notable improvements in classification performance, the network architectures used in these approaches primarily focus on exploiting the features of individual images, leaving room for improvement in capturing rich representations. In this study, we introduce a Hierarchical Graph of Nodes designed to simultaneously present representations at both feature and category levels. At the feature level, we introduce a local graph to identify the most relevant patches within an image, facilitating adaptability to defined main object representations. At the category level, we employ a global graph to aggregate the features from samples within the same category, thereby enriching overall representations. Extensive experiments on widely used SSDA benchmark datasets, including Office-Home, DomainNet, and VisDA2017, demonstrate that both quantitative and qualitative results substantiate the effectiveness of HiGDA, establishing it as a new state-of-the-art method.

Kartik Narayan, Vibashan Vs, Vishal M. Patel

Face parsing refers to the semantic segmentation of human faces into key facial regions such as eyes, nose, hair, etc. It serves as a prerequisite for various advanced applications, including face editing, face swapping, and facial makeup, which often require segmentation masks for classes like eyeglasses, hats, earrings, and necklaces. These infrequently occurring classes are called long-tail classes, which are overshadowed by more frequently occurring classes known as head classes. Existing methods, primarily CNN-based, tend to be dominated by head classes during training, resulting in suboptimal representation for long-tail classes. Previous works have largely overlooked the problem of poor segmentation performance of long-tail classes. To address this issue, we propose SegFace, a simple and efficient approach that uses a lightweight transformer-based model which utilizes learnable class-specific tokens. The transformer decoder leverages class-specific tokens, allowing each token to focus on its corresponding class, thereby enabling independent modeling of each class. The proposed approach improves the performance of long-tail classes, thereby boosting overall performance. To the best of our knowledge, SegFace is the first work to employ transformer models for face parsing. Moreover, our approach can be adapted for low-compute edge devices, achieving 95.96 FPS. We conduct extensive experiments demonstrating that SegFace significantly outperforms previous state-of-the-art models, achieving a mean F1 score of 88.96 (+2.82) on the CelebAMask-HQ dataset and 93.03 (+0.65) on the LaPa dataset.

JeongYeon Nam, Jinbae Im, Wonjae Kim, Taeho Kil

Recent vision-language generative models still frequently produce outputs misaligned with their inputs, evidenced by object hallucination in captioning and prompt misalignment in the text-to-image generation model. Recent studies have explored methods for identifying misaligned elements, aiming not only to enhance interpretability but also to improve model performance. However, current approaches primarily rely on large foundation models in a zero-shot manner or fine-tuned models with human annotations, which limits scalability due to significant computational costs. This work proposes a novel approach, dubbed CLIP4DM, for detecting dense misalignments from pre-trained CLIP, specifically focusing on pinpointing misaligned words between image and text. We carefully revamp the gradient-based attribution computation method, enabling negative gradient of individual text tokens to indicate misalignment. We also propose F-CLIPScore, which aggregates misaligned attributions with a global alignment score. We evaluate our method on various dense misalignment detection benchmarks, covering various image and text domains and misalignment types. Our method demonstrates state-of-the-art performance among zero-shot models and competitive performance with fine-tuned models while maintaining superior efficiency. Our qualitative examples show that our method has a unique strength to detect entity-level objects, intangible objects, and attributes that can not be easily detected for existing works. We conduct ablation studies and analyses to highlight the strengths and limitations of our approach.