Deep learning has achieved notable success in 3D object detection with the advent of large-scale point cloud datasets. However, severe performance degradation in the past trained classes, i.e., catastrophic forgetting, still remains a critical issue for real-world deployment when the number of classes is unknown or may vary. Moreover, existing 3D class-incremental detection methods are developed for the single-domain scenario, which fail when encountering domain shift caused by different datasets, varying environments, etc. In this paper, we identify the unexplored yet valuable scenario, i.e., class-incremental learning under domain shift, and propose a novel 3D domain adaptive class-incremental object detection framework, DA-CIL, in which we design a novel dual-domain copy-paste augmentation method to construct multiple augmented domains for diversifying training distributions, thereby facilitating gradual domain adaptation. Then, multi-level consistency is explored to facilitate dual-teacher knowledge distillation from different domains for domain adaptive class-incremental learning. Extensive experiments on various datasets demonstrate the effectiveness of the proposed method over baselines in the domain adaptive class-incremental learning scenario.
KDDI Research（KDDI研究所）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；ByteDance（字节跳动）
Continual learning (CL) learns a sequence of tasks incrementally. There are two popular CL settings, class incremental learning (CIL) and task incremental learning (TIL). A major challenge of CL is catastrophic forgetting (CF). While a number of techniques are already available to effectively overcome CF for TIL, CIL remains to be highly challenging. So far, little theoretical study has been done to provide a principled guidance on how to solve the CIL problem. This paper performs such a study. It first shows that probabilistically, the CIL problem can be decomposed into two sub-problems: With…
C3Box: A CLIP-based Class-Incremental Learning Toolbox
School of Artificial Intelligence, Nanjing University（人工智能学院，南京大学）；National Key Laboratory for Novel Software Technology, Nanjing University（新型软件技术国家实验室，南京大学）
This paper proposes two novel knowledge transfer techniques for class-incremental learning (CIL). First, we propose data-free generative replay (DF-GR) to mitigate catastrophic forgetting in CIL by using synthetic samples from a generative model. In the conventional generative replay, the generative model is pre-trained for old data and shared in extra memory for later incremental learning. In our proposed DF-GR, we train a generative model from scratch without using any training data, based on the pre-trained classification model from the past, so we curtail the cost of sharing pre-trained ge…
Continual Adapter Tuning with Semantic Shift Compensation for Class-Incremental Learning
HUST AI & Visual Learning Lab (HAIV Lab)（华中科技大学人工智能与视觉学习实验室）；Huazhong University of Science and Technology (HUST)（华中科技大学）；Department of Computer Science（计算机科学系）；Boston University（波士顿大学）；ByteDance, Inc.（字节跳动公司）
When Classes Evolve: A Benchmark and Framework for Stage-Aware Class-Incremental Learning
Dalian University of Technology（大连理工大学）；Hefei Institutes of Physical Science, Chinese Academy of Sciences（合肥物理科学研究院，中国科学院）；University of Science and Technology of China（中国科学技术大学）
We propose a causal framework to explain the catastrophic forgetting in Class-Incremental Learning (CIL) and then derive a novel distillation method that is orthogonal to the existing anti-forgetting techniques, such as data replay and feature/label distillation. We first 1) place CIL into the framework, 2) answer why the forgetting happens: the causal effect of the old data is lost in new training, and then 3) explain how the existing techniques mitigate it: they bring the causal effect back. Based on the framework, we find that although the feature/label distillation is storage-efficient, it…
Online Hyperparameter Optimization for Class-Incremental Learning
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Saarland Informatics Campus（萨尔兰信息学园区）；California Institute of Technology（加州理工学院）；Singapore Management University（新加坡管理大学）
Rotation Augmented Distillation for Exemplar-Free Class Incremental Learning with Detailed Analysis
School of Artificial Intelligence, Sun Yat-sen University（中山大学人工智能学院）；Guangdong Key Laboratory of Big Data Analysis and Processing（广东省大数据分析与处理重点实验室）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（教育部机器智能与先进计算重点实验室）
L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning
Shien-Ming Wu School of Intelligent Engineering, South China University of Technology, Guangzhou, China（华南理工大学智能工程学院）；School of Future Technology, South China University of Technology, Guangzhou, China（华南理工大学未来技术学院）；Guangdong Laboratory of Artificial Intelligence（人工智能与数字经济广东省实验室）
PrePrompt: Predictive prompting for class incremental learning
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Department of Mathematics and Statistics, Beijing Technology and Business University（北京科技商务大学数学与统计学系）；College of Science, Shantou University（汕头大学科学学院）
Seoul National University（首尔国立大学）；Sungkyunkwan University（成均馆大学）
We consider class incremental learning (CIL) problem, in which a learning agent continuously learns new classes from incrementally arriving training data batches and aims to predict well on all the classes learned so far. The main challenge of the problem is the catastrophic forgetting, and for the exemplar-memory based CIL methods, it is generally known that the forgetting is commonly caused by the classification score bias that is injected due to the data imbalance between the new classes and the old classes (in the exemplar-memory). While several methods have been proposed to correct such s…
Dynamic Feature Learning and Matching for Class-Incremental Learning
Macau University of Science and Technology（澳门科技大学）；State Key Laboratory of Multimodal Artificial Intelligence Systems（多模态人工智能系统国家重点实验室）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning
Warsaw University of Technology（华沙理工大学）；IDEAS NCBR；Jagiellonian University（雅盖隆大学）；Gdańsk University of Technology（格但斯克理工大学）；Autonomous University of Barcelona（巴塞罗那自治大学）；Computer Vision Center（计算机视觉中心）；Tooploox
REAL: Representation Enhanced Analytic Learning for Exemplar-free Class-incremental Learning
Shien-Ming Wu School of Intelligent Engineering（申铭武智能工程学院）；School of Future Technology（未来技术学院）；Department of Electrical and Electronic Engineering（电气与电子工程系）
Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning
School of Artificial Intelligence, OPtics and ElectroNics, Northwestern Polytechnical University（人工智能学院、光学与电子学院、西北工业大学）；Institute of Artificial Intelligence (TeleAI) of China Telecom（中国电信人工智能研究院）；School of Computer Science & School of Artificial Intelligence, Shanghai Jiao Tong University（计算机科学学院及人工智能学院、上海交通大学）；University of Hong Kong（香港大学）
Enhancing Plasticity for First Session Adaptation Continual Learning
LTCI, Télécom-Paris, Institut Polytechnique de Paris（Télécom-Paris 工程院）；University of Bergamo（贝加莫大学）；Inria at University Grenoble Alpes, LJK（格勒诺布尔阿尔卑斯大学）
Class-incremental Learning for Time Series: Benchmark and Evaluation
NTU（南洋理工大学）；Ho Chi Minh University of Science, Vietnam National University（越南国家大学胡志明市自然科学大学）；Qatar University（卡塔尔大学）；School of Electrical and Electronic Engineering, NTU（南洋理工大学电气与电子工程学院）
FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
Universitat Autònoma de Barcelona（巴塞罗那自治大学）；Computer Vision Center, Barcelona University of Chinese Academy of Sciences（巴塞罗那大学计算机视觉中心，中国科学院）；State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所机器人学国家重点实验室）；Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences（中国科学院机器人与智能制造研究所）
Peking University Shenzhen Graduate School（北京大学深圳研究生院）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）
Class-Incremental Learning (CIL) struggles with catastrophic forgetting when learning new knowledge, and Data-Free CIL (DFCIL) is even more challenging without access to the training data of previously learned classes. Though recent DFCIL works introduce techniques such as model inversion to synthesize data for previous classes, they fail to overcome forgetting due to the severe domain gap between the synthetic and real data. To address this issue, this paper proposes relation-guided representation learning (RRL) for DFCIL, dubbed R-DFCIL. In RRL, we introduce relational knowledge distillation…
Quantum-Gated Task-interaction Knowledge Distillation for Pre-trained Model-based Class-Incremental Learning
School of Information and Communication Engineering, BUPT（北京邮电大学信息与通信工程学院）；BUPT: Beijing University of Posts and Telecommunications（北京邮电大学）；Engineering Research Center for Information Network, Ministry of Education（教育部信息网络工程研究中心）
Improving Forward Compatibility in Class Incremental Learning by Increasing Representation Rank and Feature Richness
LINE Investment Technologies（LINE投资技术公司）；Seoul National University（首尔大学）；LG AI Research（LG人工智能研究院）；Research Institute for Convergence Science, Seoul National University（首尔大学融合科学研究院）
CI-CBM: Class-Incremental Concept Bottleneck Model for Interpretable Continual Learning
Department of Electrical and Computer Engineering, University of California San Diego（加州大学圣地亚哥分校电气与计算机工程系）；Department of Computer Science and Engineering, University of California San Diego（加州大学圣地亚哥分校计算机科学与工程系）；Halıcıoğlu Data Science Institute, University of California San Diego（加州大学圣地亚哥分校Halıcıoğlu数据科学研究所）
Wakening Past Concepts without Past Data: Class-Incremental Learning from Online Placebos
Johns Hopkins University（约翰斯·霍普金斯大学）；Max Planck Institute for Informatics, Saarland Informatics Campus（马克斯·普朗克信息学研究所，萨尔兰信息学园区）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Singapore Management University（新加坡管理大学）
Nankai University（南开大学）；University of Florence（佛罗伦萨大学）；Tencent Youtu Lab（腾讯优图实验室）
In class incremental learning (CIL) a model must learn new classes in a sequential manner without forgetting old ones. However, conventional CIL methods consider a balanced distribution for each new task, which ignores the prevalence of long-tailed distributions in the real world. In this work we propose two long-tailed CIL scenarios, which we term ordered and shuffled LT-CIL. Ordered LT-CIL considers the scenario where we learn from head classes collected with more samples than tail classes which have few. Shuffled LT-CIL, on the other hand, assumes a completely random long-tailed distributio…
Dynamic Residual Classifier for Class Incremental Learning
Sun Yat-sen University（中山大学）；Guangdong Key Laboratory of Big Data Analysis and Processing（广东省大数据分析与处理重点实验室）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（教育部机器智能与先进计算重点实验室）
South China University of Technology（华南理工大学）；Southern University of Science and Technology（南方科技大学）；Shenzhen Institute, Hunan University（湖南大学深圳研究院）；Pazhou Lab（琶洲实验室）
Noah’s Ark Lab, Huawei Technologies（华为技术诺亚方舟实验室）；McMaster University（麦克马斯特大学）；University of Manitoba（曼尼托巴大学）
Few-shot class-incremental learning (FSCIL) has been proposed aiming to enable a deep learning system to incrementally learn new classes with limited data. Recently, a pioneer claims that the commonly used replay-based method in class-incremental learning (CIL) is ineffective and thus not preferred for FSCIL. This has, if truth, a significant influence on the fields of FSCIL. In this paper, we show through empirical results that adopting the data replay is surprisingly favorable. However, storing and replaying old data can lead to a privacy concern. To address this issue, we alternatively prop…
