在广义类别发现（GCD）中，我们利用已知类别的训练数据集，对已知类别和新类别的无标签样本进行聚类。由于这些数据集之间存在域偏移，一个突出挑战随之产生。为解决该问题，我们提出了一种新设定：跨域广义类别发现（AD-GCD），并推出 CDAD-NET（Class Discoverer Across Domains，跨域类别发现器）作为解决方案。CDAD-NET 的架构旨在同步有标签（源）数据集和无标签（目标）数据集中潜在的已知类别样本，同时强调目标数据的独特分类。为实现这一点，我们提出了一种熵驱动的对抗学习策略，该策略考虑目标样本相对于源域类别原型的距离分布。同时，通过融合三个度量学习目标来维持共享空间的判别性。在源域中，我们专注于优化样本与其所属类别原型之间的邻近性；而在目标域中，我们集成了一种以邻域为中心的对比学习机制，并辅以精巧的邻居挖掘方法。为进一步突出语义对齐图像之间细微的特征关联，我们倡导条件图像修复的概念，强调如下前提：语义相似的图像比彼此脱节的图像对该任务更有效。实验方面，在我们提出的三个 AD-GCD 基准上，CDAD-NET 超越现有文献，性能提升 8–15%。
英文摘要：
In Generalized Category Discovery (GCD), we cluster unlabeled samples of known and novel classes, leveraging a training dataset of known classes. A salient challenge arises due to domain shifts between these datasets. To address this, we present a novel setting: Across Domain Generalized Category Discovery (AD-GCD) and bring forth CDAD-NET (Class Discoverer Across Domains) as a remedy. CDAD-NET is architected to synchronize potential known class samples across both the labeled (source) and unlabeled (target) datasets, while emphasizing the distinct categorization of the target data. To facilitate this, we propose an entropy-driven adversarial learning strategy that accounts for the distance distributions of target samples relative to source-domain class prototypes. Parallelly, the discriminative nature of the shared space is upheld through a fusion of three metric learning objectives. In the source domain, our focus is on refining the proximity between samples and their affiliated class prototypes, while in the target domain, we integrate a neighborhood-centric contrastive learning mechanism, enriched with an adept neighborsmining approach. To further accentuate the nuanced feature interrelation among semantically aligned images, we champion the concept of conditional image inpainting, underscoring the premise that semantically analogous images prove more efficacious to the task than their disjointed counterparts. Experimentally, CDAD-NET eclipses existing literature with a performance increment of 8-15% on three AD-GCD benchmarks we present.
Can we train a hybrid discriminative-generative model within a single network? This question has recently been answered in the affirmative, introducing the field of Joint Energy-based Model (JEM), which achieves high classification accuracy and image generation quality simultaneously. Despite recent advances, there remain two performance gaps: the accuracy gap to the standard softmax classifier, and the generation quality gap to state-of-the-art generative models. In this paper, we introduce a variety of training techniques to bridge the accuracy gap and the generation quality gap of JEM. 1) W…
The University of Sydney（悉尼大学）；SenseTime, Inc.（商汤科技）
Few-shot segmentation focuses on the generalization of models to segment unseen object instances with limited training samples. Although tremendous improvements have been achieved, existing methods are still constrained by two factors. (1) The information interaction between query and support images is not adequate, leaving intra-class gap. (2) The object categories at the training and inference stages have no overlap, leaving the inter-class gap. Thus, we propose a framework, BriNet, to bridge these gaps. First, more information interactions are encouraged between the extracted features of th…
Bridging Supervision Gaps: A Unified Framework for Remote Sensing Change Detection
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China（测绘遥感信息工程国家重点实验室，武汉大学，中国）；The University of Tokyo, Tokyo, Japan（东京大学，日本）
Bridging the Gaps: Utilizing Unlabeled Face Recognition Datasets to Boost Semi-Supervised Facial Expression Recognition
West China Hospital, Sichuan University（四川大学华西医院）；Institutes for Systems Genetics（系统遗传学研究所）；Frontiers Science Center for Disease-related Molecular Network（疾病相关分子网络前沿科学中心）
Bridging Annotation Gaps: Transferring Labels to Align Object Detection Datasets
National University of Singapore I2R, A*STAR（新加坡国立大学I2R，A*STAR）；University of Cambridge（剑桥大学）；National University of Singapore ASUS Intelligent Cloud Services（新加坡国立大学ASUS智能云服务）
Self-Supervised Enhancement of Forward-Looking Sonar Images: Bridging Cross-Modal Degradation Gaps through Feature Space Transformation and Multi-Frame Fusion
College of Electronic Engineering, Naval University of Engineering（电子工程学院，海军工程大学）；College of Meteorology and Oceanography, National University of Defense Technology（气象海洋学院，国防科技大学）；College of Computer Science and Technology, National University of Defense Technology（计算机科学与技术学院，国防科技大学）；Department of Computer Science and Technology, Tsinghua University（计算机科学与技术系，清华大学）
Bridging Semantic Logic Gaps: A Cognition Inspired Multimodal Boundary Preserving Network for Image Manipulation Localization
School of Computer Science and Technology, Xinjiang University（新疆大学计算机科学与技术学院）；School of Electronic and Information Engineering, Shenzhen University（深圳大学电子与信息工程学院）；College of Computer Science and Electronic Engineering, Hunan University（湖南大学计算机科学与电子工程学院）；School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机科学与信息工程学院）
IntentVCNet: Bridging Spatio-Temporal Gaps for Intention-Oriented Controllable Video Captioning
University of Science and Technology of China（中国科学技术大学）；Hefei Institutes of Physical Science,Chinese Academy of Sciences（合肥物理研究所，中国科学院）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（人工智能研究所，合肥综合性国家科学中心）；State Key Lab. for Novel Software Technology, Nanjing University（新型软件技术国家重点实验室，南京大学）；University of Chicago（芝加哥大学）；National University of Defense Technology（国防科技大学）；Harbin Institute of Technology（哈尔滨工业大学）
Sim2Real domain adaptation (DA) research focuses on the constrained setting of adapting from a labeled synthetic source domain to an unlabeled or sparsely labeled real target domain. However, for high-stakes applications (e.g. autonomous driving), it is common to have a modest amount of human-labeled real data in addition to plentiful auto-labeled source data (e.g. from a driving simulator). We study this setting of supervised sim2real DA applied to 2D object detection. We propose Domain Translation via Conditional Alignment and Reweighting (CARE) a novel algorithm that systematically exploits…
GeoSeg-OV: Bridging Geospatial Gaps with Structural Guidance for Open-Vocabulary Remote Sensing Segmentation
School of Computer Science, China University of Geosciences（中国地质大学计算机学院）；Systems Hub, The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）系统中心）；Department of Computer Science, City University of Hong Kong（香港城市大学计算机系）；School of Geodesy and Geomatics, Wuhan University（武汉大学测绘学院）；Data Science and AI Innovation Research Promotion Center, Shiga University（滋贺大学数据科学与人工智能创新研究促进中心）
Adaptive Dual-Teacher Distillation with Subnetwork Rectification for Bridging Semantic Gaps in Black-Box Domain Adaptation
School of Computer Science and Engineering, Tianjin University of Technology（天津理工大学计算机科学与工程学院）；School of Artificial Intelligence, Tianjin University（天津大学人工智能学院）
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Cleveland State University（克利夫兰州立大学）；Northwestern University（西北大学）
Existing multi-agent perception algorithms usually select to share deep neural features extracted from raw sensing data between agents, achieving a trade-off between accuracy and communication bandwidth limit. However, these methods assume all agents have identical neural networks, which might not be practical in the real world. The transmitted features can have a large domain gap when the models differ, leading to a dramatic performance drop in multi-agent perception. In this paper, we propose the first lightweight framework to bridge such domain gaps for multi-agent perception, which can be …
Graduate School of Info. Sci. \& Eng. Ritsumeikan University, Osaka, Japan；College of Info. Sci. \& Eng. Ritsumeikan University, Osaka, Japan；Faculty of Sci.；Eng. Soka University, Tokyo, Japan；Research Organization of Sci. \& Tech. Ritsumeikan University, Shiga, Japan；Graduate School of Informatics Kyoto University, Kyoto, Japan
Artificial Intelligence in Rural Healthcare Delivery: Bridging Gaps and Enhancing Equity through Innovation
University of Illinois College of Medicine Rockford（伊利诺伊大学罗克福德医学院）；National Center for Rural Health Professions（农村健康专业中心）；Sri Sivasubramaniya Nadar College of Engineering（塞维萨布拉曼尼亚那德尔工程学院）；M. Kumarasamy College of Engineering（M. Kumarasamy 工程学院）；The Ohio State University Wexner Medical Center（俄亥俄州立大学韦克斯纳医疗中心）；iWorks Corporation（iWorks 公司）；Central South University（中南大学）；Bacha Khan University（巴哈汗大学）
