Utilizing well-trained representations in transfer learning often results in superior performance and faster convergence compared to training from scratch. However, even if such good representations are transferred, a model can easily overfit the limited training dataset and lose the valuable properties of the transferred representations. This phenomenon is more severe in ViT due to its low inductive bias. Through experimental analysis using attention maps in ViT, we observe that the rich representations deteriorate when trained on a small dataset. Motivated by this finding, we propose a novel and simple regularization method for ViT called Guided Transfer of spatial Attention (GTA). Our proposed method regularizes the self-attention maps between the source and target models. A target model can fully exploit the knowledge related to object localization properties through this explicit regularization. Our experimental results show that the proposed GTA consistently improves the accuracy across five benchmark datasets especially when the number of training data is small.
Multimodal-Guided Dynamic Dataset Pruning for Robust and Efficient Data-Centric Learning
National Key Laboratory for Novel Software Technology, Nanjing University(新型软件技术国家重点实验室,南京大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);The Chinese University of Hong Kong(香港中文大学)
Geometric-Guided Few-Shot Dental Landmark Detection with Human-Centric Foundation Model
Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR, China(电子与计算机工程系,香港科学与技术大学);Division of Paediatric Dentistry and Orthodontics, Faculty of Dentistry, The University of Hong Kong, Hong Kong SAR, China(牙科学院儿童牙科与正畸学系,香港大学)
Vehicle-centric Perception via Multimodal Structured Pre-training
Information Materials and Intelligent Sensing Laboratory of Anhui Province(安徽省信息材料与智能感知实验室);Anhui Provincial Key Laboratory of Multimodal Cognitive Computation(安徽省多模态认知计算重点实验室);the School of Artificial Intelligence, Anhui University(安徽大学人工智能学院);School of Computer Science and Technology, Anhui University(安徽大学计算机科学与技术学院);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(合肥综合性国家科学中心人工智能研究院)
Instance Adaptive Self-Training for Unsupervised Domain Adaptation
Beijing University of Posts and Telecommunications(北京邮电大学);University of California, Berkeley(加州大学伯克利分校)
标记的训练数据和未标记的测试数据之间的分歧是最近深度学习模型的一个重大挑战。无监督领域自适应(UDA)试图解决这样的问题。最近的工作表明,自我训练是一个强大的方法UDA。然而,现有的方法在平衡可扩展性和性能方面存在困难。在本文中,我们提出了一个实例自适应自训练框架的UDA任务的语义分割。为了有效地提高伪标签的质量,我们开发了一种新的伪标签生成策略与实例自适应选择器。此外,我们还提出了区域引导的正则化方法来平滑伪标记区域和锐化非伪标记区域。该方法简洁高效,易于推广到其他无监督领域自适应方法。在“GTA5 to Cityscapes”和“SYNTHIA to Cityscapes”上的实验表明,与最先进的方法相比,我们的方法具有更好的性能。
UniEmoX: Cross-modal Semantic-Guided Large-Scale Pretraining for Universal Scene Emotion Perception
School of Artificial Intelligence, Anhui University(安徽大学人工智能学院);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(合肥国家综合科学中心人工智能研究所);Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machines, School of Computer Science and Information Engineering, Hefei University of Technology(安徽省情感计算与先进智能机器重点实验室,合肥工业大学计算机科学与信息工程学院);Department of Computer and Network Engineering, The University of Electro-Communications(电子通信大学计算机与网络工程系)
CLIP-Guided Adaptable Self-Supervised Learning for Human-Centric Visual Tasks
Key Laboratory of Intelligent Information Processing, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), and University of Chinese Academy of Sciences(智能信息处理重点实验室,计算技术研究所(ICT),中国科学院(CAS)及中国科学院大学)
Top-Down Guidance for Learning Object-Centric Representations
MAIS, Institute of Automation, Chinese Academy of Sciences(自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);CAIR, HKSIS, Chinese Academy of Sciences(中国科学院计算机研究所);School of Computer Science and Engineering, the Faculty of Innovation Engineering, M.U.S.T(澳门科技大学计算机科学与工程学院)
From Gaze to Meaning: A Training-Free AI Agent for Unified Grounding and Explanation
Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey(萨里大学视觉、语音与信号处理中心);Surrey Institute for People-Centred AI, University of Surrey(萨里大学以人为本人工智能研究所)
Prompt-Driven Dynamic Object-Centric Learning for Single Domain Generalization
College of Intelligence and Computing, Tianjin University(天津大学智能与计算学部);School of Electronic Engineering, Xidian University(西安电子科技大学电子工程学院);Peng Cheng Laboratory(鹏城实验室)