Hierarchical Invariance for Robust and Interpretable Vision Tasks at Larger Scales
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics（南京航空航天大学计算机科学与技术学院）；College of Cyber Security, Jinan University（暨南大学网络安全学院）；School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区网络空间安全学院）
Developing robust and interpretable vision systems is a crucial step towards trustworthy artificial intelligence. In this regard, a promising paradigm considers embedding task-required invariant structures, e.g., geometric invariance, in the fundamental image representation. However, such invariant representations typically exhibit limited discriminability, limiting their applications in larger-scale trustworthy vision tasks. For this open problem, we conduct a systematic investigation of hierarchical invariance, exploring this topic from theoretical, practical, and application perspectives. At the theoretical level, we show how to construct over-complete invariants with a Convolutional Neural Networks (CNN)-like hierarchical architecture yet in a fully interpretable manner. The general blueprint, specific definitions, invariant properties, and numerical implementations are provided. At the practical level, we discuss how to customize this theoretical framework into a given task. With the over-completeness, discriminative features w.r.t. the task can be adaptively formed in a Neural Architecture Search (NAS)-like manner. We demonstrate the above arguments with accuracy, invariance, and efficiency results on texture, digit, and parasite classification experiments. Furthermore, at the application level, our representations are explored in real-world forensics tasks on adversarial perturbations and Artificial Intelligence Generated Content (AIGC). Such applications reveal that the proposed strategy not only realizes the theoretically promised invariance, but also exhibits competitive discriminability even in the era of deep learning. For robust and interpretable vision tasks at larger scales, hierarchical invariant representation can be considered as an effective alternative to traditional CNN and invariants.
Unlocking Biomedical Insights: Hierarchical Attention Networks for High-Dimensional Data Interpretation
Department of Computer Science and Engineering, Alliance University（计算机科学与工程系，联盟大学）；College of Engineering and IT, University of Dubai（工程与信息技术学院，迪拜大学）；Shiv Nadar University（施瓦纳达大学）
The Horcrux: Mechanistically Interpretable Task Decomposition for Detecting and Mitigating Reward Hacking in Embodied AI Systems
Berkeley AI Safety Initiative (BASIS) UC Berkeley（伯克利人工智能安全计划（BASIS）伯克利大学）；Department of Electrical and Computer Engineering Johns Hopkins University（电气与计算机工程系约翰霍普金斯大学）
Decontextualized learning for interpretable hierarchical representations of visual patterns
Max Planck Institute of Animal Behavior（马克斯·普朗克动物行为研究所）；University of Konstanz（康斯坦茨大学）；Centro de Investigaciones Científicas de las Huastecas Aguazarca, A.C.（华斯特卡斯阿瓜扎尔卡科学研究中心）；University of Würzburg（维尔茨堡大学）；Texas A&M University（得克萨斯农工大学）；Texas State University San Marcos（得克萨斯州立大学圣马科斯分校）
Interpretable Single-View 3D Gaussian Splatting using Unsupervised Hierarchical Disentangled Representation Learning
Shanghai Jiao Tong University（上海交通大学）；Ningbo Institute of Digital Twin, Eastern Institute of Technology（东方理工大学宁波数字孪生研究院）；Hong Kong Polytechnic University（香港理工大学）
Hierarchical Vision Transformer with Prototypes for Interpretable Medical Image Classification
Ulm University Medical Center（乌尔姆大学医学中心）；BGZ - Bildgebungszentrum（BGZ影像中心）；i2SouI - Innovative Imaging in Surgical Oncology Ulm（乌尔姆外科肿瘤创新影像中心）；XAIRAD - Cooperation for Artificial Intelligence in Experimental Radiology（XAIRAD实验放射学人工智能合作中心）
Hierarchical Salient Patch Identification for Interpretable Fundus Disease Localization
School of Electronic and Information Engineering, Tongji University（同济大学电子与信息工程学院）；Shanghai Eye Disease Prevention and Treatment Center（上海眼病防治中心）；School of Information Science and Technology, Fudan University（复旦大学信息科学与技术学院）
SurfAge-Net: A Hierarchical Surface-Based Network for Interpretable Fine-Grained Brain Age Prediction
Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University（甘肃省可穿戴计算重点实验室，信息科学与工程学院，兰州大学）；Department of Medical Imaging Center, Gansu Provincial Maternity and Child-Care Hospital（医学影像中心，甘肃省妇幼保健院）；Department of Magnetic Resonance, Lanzhou University Second Hospital（磁共振科，兰州大学第二医院）；Department of Computer Science and Technology, Harbin Institute of Technology (Shenzhen)（计算机科学与技术系，哈尔滨工业大学（深圳））；Key Laboratory for Biomedical Engineering of Ministry of Education, Department of Biomedical Engineering, College of Biomedical Engineering & Instrument Science, Zhejiang University（教育部生物医学工程重点实验室，生物医学工程学院，浙江大学）
Bodhi VLM: Privacy-Alignment Modeling for Hierarchical Visual Representations in Vision Backbones and VLM Encoders via Bottom-Up and Top-Down Feature Search
Auckland University of Technology（奥克兰技术大学）；Resideo Technologies, Inc.（Resideo技术公司）；Guilin University of Electronic Technology（桂林电子科技大学）；Universidad de Chile（智利大学）
