The softmax cross-entropy loss function has been widely used to train deep models for various tasks. In this work, we propose a Gaussian mixture (GM) loss function for deep neural networks for visual classification. Unlike the softmax cross-entropy loss, our method explicitly shapes the deep feature space towards a Gaussian Mixture distribution. With a classification margin and a likelihood regularization, the GM loss facilitates both high classification performance and accurate modeling of the feature distribution. The GM loss can be readily used to distinguish abnormal inputs, such as the adversarial examples, based on the discrepancy between feature distributions of the inputs and the training set. Furthermore, theoretical analysis shows that a symmetric feature space can be achieved by using the GM loss, which enables the models to perform robustly against adversarial attacks. The proposed model can be implemented easily and efficiently without using extra trainable parameters. Extensive evaluations demonstrate that the proposed method performs favorably not only on image classification but also on robust detection of adversarial examples generated by strong attacks under different threat models.
ANTS: Adaptive Negative Textual Space Shaping for OOD Detection via Test-Time MLLM Understanding and Reasoning
The Hong Kong Polytechnic University（香港理工大学）；Eastern Institute of Technology, Ningbo（宁波东部技术研究院）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Zhongguancun Academy（中关村学院）
Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images
King Abdullah University of Science and Technology（国王阿卜杜勒·阿齐兹大学科学与技术学院）；Provable Responsible AI and Data Analytics Lab（可证责任AI与数据分析实验室）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；China University of Petroleum-Beijing at Karamay（北京石油大学克拉玛依校区）
SPOT-E: Test-Time Entropy Shaping with Visual Spotlights for Frozen VLMs
National University of Singapore（新加坡国立大学）；Fudan University（复旦大学）；Technical University of Munich（慕尼黑工业大学）；Sagenic Tech；Zhejiang University（浙江大学）；vivo；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Gaussian Mixture Modeling for Event-Aware Visual Allocation in Long Video Understanding
Beijing Key Laboratory of Super Intelligent Security of Multi-Modal Information, CASIA（中国科学院自动化所多模态信息超智能安全北京市重点实验室）；State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA（中国科学院自动化所多模态人工智能系统国家重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Hello Group（未知（保留英文））；School of Information Science and Technology, ShanghaiTech University（上海科技大学信息科学与技术学院）
Mixture-of-Visual-Thoughts: Exploring Context-Adaptive Reasoning Mode Selection for General Visual Reasoning
Fudan University（复旦大学）；Alibaba Group Holding Limited（阿里巴巴集团控股有限公司）；Future Living Lab of Alibaba（阿里巴巴未来生活实验室）；University of Southern California（南加州大学）；Shanghai Innovation Institute（上海创新研究院）
Gaze on the Prize: Shaping Visual Attention with Return-Guided Contrastive Learning
Department of Computer Science University of California Davis（加州大学戴维斯分校计算机科学系）；Department of Electrical Engineering and Computer Sciences University of California Berkeley（加州大学伯克利分校电气工程与计算机科学系）；Department of Mechanical and Aerospace Engineering University of California Davis（加州大学戴维斯分校机械与航空航天工程系）
Gaze on the Prize通过回报引导的对比学习，提升视觉强化学习的样本效率，解决ManiSkill3基准中难以学习的任务。
ActVAR: Activating Mixtures of Weights and Tokens for Efficient Visual Autoregressive Generation
School of Computer Science and Engineering, Central South University（中南大学计算机科学与工程学院）；University of Electronic Science and Technology of China（电子科技大学）；School of Computer Science, Peking University（北京大学计算机科学学院）；SenseTime Research（商汤科技研究院）；Shanghai Jiao Tong University（上海交通大学）
EmbodiedPlace: Learning Mixture-of-Features with Embodied Constraints for Visual Place Recognition
Southern University of Science and Technology, Shenzhen, China（南方科技大学）；Peng Cheng Laboratory, Shenzhen, China（鹏城实验室）；University of Cambridge, Cambridge, United Kingdom（剑桥大学）；Northeastern University, China（东北大学）；MAIS, Institution of Automation, China Academic of Sciences, Beijing, China（自动化研究所）
BioMedVR: Confusion-Aware Mixture-of-Prompt Experts for Biomedical Visual Reprogramming
Guangdong Institute of Intelligence Science and Technology（广东智能科技研究院）；Zhejiang University（浙江大学）；Southeast University（东南大学）；The Hong Kong Polytechnic University（香港理工大学）；Institute of Science Tokyo（东京科学大学）；Shanghai Jiao Tong University（上海交通大学）
Sparse Mixture-of-Experts Routing in Visual Diffusion Transformers:Diagnosis, Boundary Calibration and Evolutionary Roadmap from Routing Collapse to Selective Deadlock
MoLE: Mixture of Latent Experts for Complementary Visual Reasoning
Tongji University（同济大学）；Hong Kong Polytechnic University（香港理工大学）；Alibaba Group（阿里巴巴集团）；University of Electronic Science and Technology of China（电子科技大学）
