Few-Shot Class Incremental Learning (FSCIL) is a challenging continual learning task, where limited training examples are available during several learning sessions. To succeed in this task, it is necessary to avoid over-fitting new classes caused by biased distributions in the few-shot training sets. The general approach to address this issue involves enhancing the representational capability of a pre-defined backbone architecture by adding special modules for backward compatibility with older classes. However, this approach has not yet solved the dilemma of ensuring high classification accuracy over time while reducing the gap between the performance obtained on larger training sets and the smaller ones. In this work, we propose an alternative approach called Continual Parameter-Efficient CLIP (CPE-CLIP) to reduce the loss of information between different learning sessions. Instead of adapting additional modules to address information loss, we leverage the vast knowledge acquired by CLIP in large-scale pre-training and its effectiveness in generalizing to new concepts. Our approach is multimodal and parameter-efficient, relying on learnable prompts for both the language and vision encoders to enable transfer learning across sessions. We also introduce prompt regularization to improve performance and prevent forgetting. Our experimental results demonstrate that CPE-CLIP significantly improves FSCIL performance compared to state-of-the-art proposals while also drastically reducing the number of learnable parameters and training costs.
Few-shot Class-Incremental Learning via Generative Co-Memory Regularization
Institute of Information Engineering(信息工程研究所);Chinese Academy of Sciences(中国科学院);School of Cyber Security(网络安全学院);University of Chinese Academy of Sciences(中国科学院大学);Department of Communication Engineering(通信工程系)
CD^2: Constrained Dataset Distillation for Few-Shot Class-Incremental Learning
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络安全学院);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
A Forward and Backward Compatible Framework for Few-shot Class-incremental Pill Recognition
National University of Defense Technology (NUDT)(国防科技大学);College of Intelligence Science and Technology(智能科学与技术学院);College of Electronic Science and Technology(电子科学与技术学院)
Optical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning
Beihang University, Beijing 100191, China(北航,北京100191,中国);Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China(航天信息研究所,中国科学院,北京100190,中国)
Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning
Australian National University(澳大利亚国立大学);Data61-CSIRO Australia(澳大利亚联邦科学与工业研究组织Data61);North South University Bangladesh(孟加拉国南北大学);Monash University Australia(澳大利亚莫纳什大学)
Rethinking Few-Shot Class-Incremental Learning with Open-Set Hypothesis in Hyperbolic Geometry
National University of Defense Technology(国防科技大学);University of Oulu(奥卢大学);Nanyang Technological University(南洋理工大学);Stanford University(斯坦福大学)
Few-Shot类增量学习(Class-Incremental Learning,FSCIL)的目标是从少量的标记样本中增量学习新类,同时避免过拟合和灾难性遗忘。FSCIL的当前协议是通过模仿一般的类增量学习设置来构建的,但是由于不同的数据配置,即,新的类都在有限的数据范围内。在本文中,我们重新考虑配置的FSCIL与开集假设保留的可能性,在第一届会议传入的类别。为了提高模型的闭集和开集识别性能,在倒易点学习(Reciprocal Point Learning,RPL)的基础上,利用双曲神经网络构建了双曲倒易点学习模块(Hyper-RPL)。此外,为了从有限的标记数据中学习新的类别,我们将双曲度量学习(Hyper-Metric)模块纳入基于蒸馏的框架中,以减轻过拟合问题,并更好地处理旧知识的保存和新知识的获取之间的权衡问题。在三个基准数据集上对所提出的配置和模块进行了全面评估,以验证三个评估指标的有效性。
On Distilling the Displacement Knowledge for Few-Shot Class-Incremental Learning
School of Computer Science and Engineering, Southeast University(东南大学计算机科学与工程学院);Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education(教育部新一代人工智能技术及交叉应用重点实验室(东南大学))
Learning New Concepts, Remembering the Old: Continual Learning for Multimodal Concept Bottleneck Models
HKUST(GZ) Deep Interdisciplinary Intelligence Lab(香港科技大学(广州)深度跨学科智能实验室);Wuhan University(武汉大学);Shandong University(山东大学);Tongji University(同济大学);Peking University(北京大学);University of Macau(澳门大学);HKUST(GZ) Institute of Deep Perception Technology, JITRI Deep Interdisciplinary Intelligence Lab(香港科技大学(广州)感知技术研究所,JITRI深度跨学科智能实验室)
SPRINT: Semi-supervised Prototypical Representation for Few-Shot Class-Incremental Tabular Learning
Department of Computer Science, Virginia Tech, Blacksburg, VA, USA(弗吉尼亚理工大学计算机科学系);DEVCOM Army Research Laboratory, Adelphi, MD, USA(陆军研究实验室);Department of Computer Science, University of Texas at Dallas, Dallas, TX, USA(德克萨斯大学达拉斯分校计算机科学系);Department of Computer Science, University of California, Irvine, CA, USA(加州大学尔湾分校计算机科学系)
MoTiC: Momentum Tightness and Contrast for Few-Shot Class-Incremental Learning
School of Computer Science and Information Security(计算机科学与信息安全学院);School of Artificial Intelligence(人工智能学院);School of Internet of Things Engineering(物联网工程学院)
Divide and Conquer: Static-Dynamic Collaboration for Few-Shot Class-Incremental Learning
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络安全学院);Department of Communication Engineering, Shanghai University(上海大学通信工程系)