Neurons Merging Layer: Towards Progressive Redundancy Reduction for Deep Supervised Hashing
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Horizon Robotics（地平线机器人）；Center for Excellence in Brain Science and Intelligence Technology, CAS（中国科学院脑科学与智能技术卓越创新中心）
Chaoyou Fu, Liangchen Song, Xiang Wu, Guoli Wang, Ran He
Deep supervised hashing has become an active topic in information retrieval. It generates hashing bits by the output neurons of a deep hashing network. During binary discretization, there often exists much redundancy between hashing bits that degenerates retrieval performance in terms of both storage and accuracy. This paper proposes a simple yet effective Neurons Merging Layer (NMLayer) for deep supervised hashing. A graph is constructed to represent the redundancy relationship between hashing bits that is used to guide the learning of a hashing network. Specifically, it is dynamically learned by a novel mechanism defined in our active and frozen phases. According to the learned relationship, the NMLayer merges the redundant neurons together to balance the importance of each output neuron. Moreover, multiple NMLayers are progressively trained for a deep hashing network to learn a more compact hashing code from a long redundant code. Extensive experiments on four datasets demonstrate that our proposed method outperforms state-of-the-art hashing methods.
Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic Hashing
School of Computer Science and Technology, University of Science and Technology of China（中国科学技术大学计算机科学与技术学院）；School of Data Science, University of Science and Technology of China（中国科学技术大学数据科学学院）；iFLYTEK AI Research（讯飞AI研究院）
Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolution
Carnegie Mellon University（卡内基梅隆大学）；Shanghai Jiao Tong University（上海交通大学）；Sun Yat-sen University（中山大学）；Snap Inc.（Snap公司）；South China University of Technology（华南理工大学）
Global Context-Aware Progressive Aggregation Network for Salient Object Detection
University of Chinese Academy of Sciences（中国科学院大学）；Key Lab. of Intelligent Information Processing, ICT, CAS（中国科学院计算技术研究所智能信息处理重点实验室）；Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学研究所）；Key Lab. of Big Data Mining and Knowledge Management, CAS（中国科学院大数据挖掘与知识管理重点实验室）；Peng Cheng Laboratory（鹏城实验室）；ICT, CAS（中国科学院计算技术研究所）
FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models
School of Computer Science and Technology, Huazhong University of Science and Technology（华中科技大学计算机科学与技术学院）；Xiaohongshu Inc.（小红书公司）；Shanghai Jiao Tong University（上海交通大学）
p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室）；China Mobile Research Institute（中国移动研究院）；Shanghai AI Lab（上海AI实验室）
Enhancing Weakly Supervised Multimodal Video Anomaly Detection through Text Guidance
School of Computer Science and Technology, Hangzhou Dianzi University（杭州电子科技大学计算机科学与技术学院）；Alibaba Cloud（阿里云）；College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）
Orthonormal Product Quantization Network for Scalable Face Image Retrieval
City University of Hong Kong（香港城市大学）；Centre for Intelligent Multidimensional Data Analysis Limited（智能多维数据分析中心有限公司）；Hong Kong Applied Science and Technology Research Institute Company Limited（香港应用科技研究院有限公司）；Tencent AI Lab（腾讯人工智能实验室）
Less is More: Selective Reduction of CT Data for Self-Supervised Pre-Training of Deep Learning Models with Contrastive Learning Improves Downstream Classification Performance
Ulm University（乌尔姆大学）；Ulm University Medical Center（乌尔姆大学医学中心）
