局部学习为深度神经网络中传统的端到端反向传播提供了替代方案,可显著降低GPU内存消耗。尽管它在图像分类任务中已展现出潜力,但向其他视觉任务的拓展仍受到限制。这一局限主要源于两个因素:1)专为分类设计的架构难以适配其他任务,导致无法有效复用针对不同问题定制的架构中的任务特定知识;2)这些聚焦分类的架构通常缺乏跨尺度特征通信,致使目标检测和超分辨率等任务的性能下降。为应对这些挑战,我们提出了特征库增强辅助网络(Feature Bank Augmented auxiliary network, FBA),该方法引入了简化的设计原则,并融入特征库以提升跨任务适配性与特征通信能力。这项工作是局部学习方法首次成功应用于分类以外的领域,证明FBA不仅能节省GPU内存,还能在多种视觉任务的多个数据集上达到与端到端方法相当的性能。
英文摘要:
Local learning offers an alternative to traditional end-to-end back-propagation in deep neural networks, significantly reducing GPU memory consumption. Although it has shown promise in image classification tasks, its extension to other visual tasks has been limited. This limitation arises primarily from two factors: 1) architectures designed specifically for classification are not readily adaptable to other tasks, which prevents the effective reuse of task-specific knowledge from architectures tailored to different problems; 2) these classification-focused architectures typically lack cross-scale feature communication, leading to degraded performance in tasks like object detection and super-resolution. To address these challenges, we propose the Feature Bank Augmented auxiliary network (FBA), which introduces a simplified design principle and incorporates a feature bank to enhance cross-task adaptability and communication. This work represents the first successful application of local learning methods beyond classification, demonstrating that FBA not only conserves GPU memory but also achieves performance on par with end-to-end approaches across multiple datasets for various visual tasks.
Double Banking on Knowledge: Customized Modulation and Prototypes for Multi-Modality Semi-supervised Medical Image Segmentation
College of Computer Science, Sichuan University(四川大学计算机学院);Agency for Science, Technology and Research (A*STAR)(新加坡科技研究局);College of Electrical Engineering, Sichuan University(四川大学电气工程学院);School of Cyber Science and Engineering, Sichuan University(四川大学网络空间安全学院)
Bridging the Gap between Labeled and Unlabeled Data via Unified Flow with Feature Memory Bank
City University of Macau(澳门城市大学);Southeast University(东南大学);Ocean University of China(中国海洋大学);Nantes Université(南特大学);Ecole Centrale Nantes(南特中央理工学院);CAPACITES SAS;CNRS(法国国家科学研究中心);LS2N(南特数字科学实验室)
Advancing Weakly-Supervised Change Detection in Satellite Images via Adversarial Class Prompting
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University(信息工程测绘遥感国家重点实验室,武汉大学);School of Computer Science and Technology, Anhui University(计算机科学与技术学院,安徽大学);Graduate School of Frontier Sciences, University of Tokyo(前沿科学研究院,东京大学);Institute of Geodesy and Photogrammetry, ETH Zürich(测绘学研究院,苏黎世联邦理工学院);Department of Computer Science, Stanford University(计算机科学系,斯坦福大学)
Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning
Key Laboratory of Machine Perception (MOE)((教育部)机器感知重点实验室);School of EECS, Peking University(北京大学电子工程与计算机科学学院);Zhejiang Lab(之江实验室);Microsoft Research Asia(微软亚洲研究院)
Harnessing Self-Supervised Deep Learning and Geostationary Remote Sensing for Advancing Wildfire and Associated Air Quality Monitoring: Improved Smoke and Fire Front Masking using GOES and TEMPO Radiance Data
Spatial Informatics Group, LLC.(空间信息集团有限责任公司);ADNET systems, INC.(ADNET系统公司);NASA Langley Research Center(美国国家航空航天局兰利研究中心);University at Albany(奥尔巴尼大学)
Advancing human-centric AI for robust X-ray analysis through holistic self-supervised learning
FAIR at Meta(Meta FAIR研究院);Hôpital Cochin, AP-HP.Centre Université Paris Cité(科钦医院、巴黎大学中心公共医疗援助系统);Université Paris Cité(巴黎大学);CentraleSupélec, Université Paris-Saclay(巴黎萨克雷大学中央理工学院)
A self-supervised learning approach to deep filter banks for texture recognition
Institute of Mathematics and Statistics of the University of Sao Paulo(圣保罗大学数学与统计学研究所);Institute of Mathematics, Statistics and Scientific Computing of the University of Campinas(坎皮纳斯大学数学、统计与科学计算研究所)
Advancing Stroke Risk Prediction Using a Multi-modal Foundation Model
Signal Processing Institute EPFL University Lausanne(瑞士洛桑联邦理工学院信号处理研究所);Brigham and Women’s Hospital Harvard Medical School(哈佛医学院布里奇沃特医院);Department of Quantitative Biomedicine University of Zurich(苏黎世大学定量生物医学系);ETH AI Center, Department of Computer Science Department of Quantitative Biomedicine University of Zurich(苏黎世大学定量生物医学系)
Advancing Real-World Parking Slot Detection with Large-Scale Dataset and Semi-Supervised Baseline
Institute of Information Science, Beijing Jiaotong University(信息科学学院,北京交通大学);Visual Intelligence +X International Cooperation Joint Laboratory of MOE(教育部视觉智能+X国际合作联合实验室)
Anomaly Detection in Electrocardiograms: Advancing Clinical Diagnosis Through Self-Supervised Learning
Shanghai Jiao Tong University(上海交通大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Ruijin Hospital, Shanghai Jiao Tong University School of Medicine(上海交通大学医学院附属瑞金医院)
Advancing Weakly-Supervised Audio-Visual Video Parsing via Segment-wise Pseudo Labeling
Hefei University of Technology(合肥工业大学);Shanghai AI Laboratory(上海人工智能实验室);Hefei Comprehensive National Science Center(合肥综合性国家科学中心);Anhui Zhonghuitong Technology Co., Ltd.(安徽中汇通科技有限公司)