Few-shot class-incremental learning (FSCIL) aims to design machine learning algorithms that can continually learn new concepts from a few data points, without forgetting knowledge of old classes. The difficulty lies in that limited data from new classes not only lead to significant overfitting issues but also exacerbate the notorious catastrophic forgetting problems. Moreover, as training data come in sequence in FSCIL, the learned classifier can only provide discriminative information in individual sessions, while FSCIL requires all classes to be involved for evaluation. In this paper, we address the FSCIL problem from two aspects. First, we adopt a simple but effective decoupled learning strategy of representations and classifiers that only the classifiers are updated in each incremental session, which avoids knowledge forgetting in the representations. By doing so, we demonstrate that a pre-trained backbone plus a non-parametric class mean classifier can beat state-of-the-art methods. Second, to make the classifiers learned on individual sessions applicable to all classes, we propose a Continually Evolved Classifier (CEC) that employs a graph model to propagate context information between classifiers for adaptation. To enable the learning of CEC, we design a pseudo incremental learning paradigm that episodically constructs a pseudo incremental learning task to optimize the graph parameters by sampling data from the base dataset. Experiments on three popular benchmark datasets, including CIFAR100, miniImageNet, and Caltech-USCD Birds-200-2011 (CUB200), show that our method significantly outperforms the baselines and sets new state-of-the-art results with remarkable advantages.
Continuous appearance shifts such as changes in weather and lighting conditions can impact the performance of deployed machine learning models. While unsupervised domain adaptation aims to address this challenge, current approaches do not utilise the continuity of the occurring shifts. In particular, many robotics applications exhibit these conditions and thus facilitate the potential to incrementally adapt a learnt model over minor shifts which integrate to massive differences over time. Our work presents an adversarial approach for lifelong, incremental domain adaptation which benefits from …
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）
The ability to learn more and more concepts over time from incrementally arriving data is essential for the development of a life-long learning system. However, deep neural networks often suffer from forgetting previously learned concepts when continually learning new concepts, which is known as catastrophic forgetting problem. The main reason for catastrophic forgetting is that the past concept data is not available and neural weights are changed during incrementally learning new concepts. In this paper, we propose a pseudo-rehearsal based class incremental learning approach to make neural ne…
University of Toronto（多伦多大学）；LG AI Research（LG人工智能研究院）
As image-based deep learning becomes pervasive on every device, from cell phones to smart watches, there is a growing need to develop methods that continually learn from data while minimizing memory footprint and power consumption. While memory replay techniques have shown exceptional promise for this task of continual learning, the best method for selecting which buffered images to replay is still an open question. In this paper, we specifically focus on the online class-incremental setting where a model needs to learn new classes continually from an online data stream. To this end, we contri…
Few-shot Class-Incremental Learning (FSCIL) aims at learning new concepts continually with only a few samples, which is prone to suffer the catastrophic forgetting and overfitting problems. The inaccessibility of old classes and the scarcity of the novel samples make it formidable to realize the trade-off between retaining old knowledge and learning novel concepts. Inspired by that different models memorize different knowledge when learning novel concepts, we propose a Memorizing Complementation Network (MCNet) to ensemble multiple models that complements the different memorized knowledge with…
IBM Research-Zurich（IBM苏黎世研究院）；ETH Zurich（苏黎世联邦理工学院）
Continually learning new classes from fresh data without forgetting previous knowledge of old classes is a very challenging research problem. Moreover, it is imperative that such learning must respect certain memory and computational constraints such as (i) training samples are limited to only a few per class, (ii) the computational cost of learning a novel class remains constant, and (iii) the memory footprint of the model grows at most linearly with the number of classes observed. To meet the above constraints, we propose C-FSCIL, which is architecturally composed of a frozen meta-learned fe…
This paper considers incremental few-shot learning, which requires a model to continually recognize new categories with only a few examples provided. Our study shows that existing methods severely suffer from catastrophic forgetting, a well-known problem in incremental learning, which is aggravated due to data scarcity and imbalance in the few-shot setting. Our analysis further suggests that to prevent catastrophic forgetting, actions need to be taken in the primitive stage -- the training of base classes instead of later few-shot learning sessions. Therefore, we propose to search for flat loc…
How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization?
Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；The Hong Kong Polytechnic University（香港理工大学）；Fudan University（复旦大学）；Australian National University（澳大利亚国立大学）；Linköping University（林雪平大学）；Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）
Indian Institute of Technology Hyderabad（印度理工学院海得拉巴分校）；PSG College Of Technology（PSG理工学院）
In class-incremental learning, the model is expected to learn new classes continually while maintaining knowledge on previous classes. The challenge here lies in preserving the model's ability to effectively represent prior classes in the feature space, while adapting it to represent incoming new classes. We propose two distillation-based objectives for class incremental learning that leverage the structure of the feature space to maintain accuracy on previous classes, as well as enable learning the new classes. In our first objective, termed cross-space clustering (CSC), we propose to use the…
University of Toronto（多伦多大学）；LG AI Research（LG人工智能研究院）
Online class-incremental continual learning (CL) studies the problem of learning new classes continually from an online non-stationary data stream, intending to adapt to new data while mitigating catastrophic forgetting. While memory replay has shown promising results, the recency bias in online learning caused by the commonly used Softmax classifier remains an unsolved challenge. Although the Nearest-Class-Mean (NCM) classifier is significantly undervalued in the CL community, we demonstrate that it is a simple yet effective substitute for the Softmax classifier. It addresses the recency bias…
Incremental learning requires a model to continually learn new tasks from streaming data. However, traditional fine-tuning of a well-trained deep neural network on a new task will dramatically degrade performance on the old task -- a problem known as catastrophic forgetting. In this paper, we address this issue in the context of anchor-free object detection, which is a new trend in computer vision as it is simple, fast, and flexible. Simply adapting current incremental learning strategies fails on these anchor-free detectors due to lack of consideration of their specific model structures. To d…
In this paper, we focus on a new and challenging decentralized machine learning paradigm in which there are continuous inflows of data to be addressed and the data are stored in multiple repositories. We initiate the study of data decentralized class-incremental learning (DCIL) by making the following contributions. Firstly, we formulate the DCIL problem and develop the experimental protocol. Secondly, we introduce a paradigm to create a basic decentralized counterpart of typical (centralized) class-incremental learning approaches, and as a result, establish a benchmark for the DCIL study. Thi…
Representation Calibration and Uncertainty Guidance for Class-Incremental Learning based on Vision Language Model
Guangdong Province Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（广东省机器智能与先进计算重点实验室）；Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；Peng Cheng Laboratory（鹏城实验室）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（广东省机器智能与先进计算重点实验室）
Integrating Task-Specific and Universal Adapters for Pre-Trained Model-based Class-Incremental Learning
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（新型软件技术国家重点实验室，南京大学）
Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning
School of Artificial Intelligence, Nanjing University（人工智能学院，南京大学）；State 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）
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）；School of Computer Science, Peking University（北京大学计算机学院）
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）
Semantic-Guided Dynamic Sparsification for Pre-Trained Model-based Class-Incremental Learning
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China（中国科学院计算技术研究所）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学）
School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）；National Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；S-Lab, College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院S-Lab）
University of Chinese Academy of Sciences（中国科学院大学）；Peking University（北京大学）；Huawei Technologies（华为技术有限公司）；Tsinghua University（清华大学）；Chinese Academy of Sciences（中国科学院）
Few-shot class-incremental learning(FSCIL) focuses on designing learning algorithms that can continually learn a sequence of new tasks from a few samples without forgetting old ones. The difficulties are that training on a sequence of limited data from new tasks leads to severe overfitting issues and causes the well-known catastrophic forgetting problem. Existing researches mainly utilize the image information, such as storing the image knowledge of previous tasks or limiting classifiers updating. However, they ignore analyzing the informative and less noisy text information of class labels. I…
Towards Non-Exemplar Semi-Supervised Class-Incremental Learning
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences（中国科学院香港创新研究院人工智能与机器人中心）
PKI: Prior Knowledge-Infused Neural Network 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 at University of Chinese Academy of Sciences（中国科学院大学网络安全学院）；NARI Technology Company Limited（NARI科技有限公司）；School of Engineering and Applied Science, the George Washington University（乔治华盛顿大学工程与应用科学学院）；Department of Communication Engineering, Shanghai University（上海大学通信工程系）
Tsinghua University（清华大学）；Peng Cheng Laboratory（鹏城实验室）；University of Connecticut（康涅狄格大学）
Deep neural networks (DNNs) have been applied in class incremental learning, which aims to solve common real-world problems of learning new classes continually. One drawback of standard DNNs is that they are prone to catastrophic forgetting. Knowledge distillation (KD) is a commonly used technique to alleviate this problem. In this paper, we demonstrate it can indeed help the model to output more discriminative results within old classes. However, it cannot alleviate the problem that the model tends to classify objects into new classes, causing the positive effect of KD to be hidden and limite…
Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）；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院）；University of Chinese Academy of Sciences（中国科学院大学）；Northeastern University（东北大学）
3D object classification has attracted appealing attentions in academic researches and industrial applications. However, most existing methods need to access the training data of past 3D object classes when facing the common real-world scenario: new classes of 3D objects arrive in a sequence. Moreover, the performance of advanced approaches degrades dramatically for past learned classes (i.e., catastrophic forgetting), due to the irregular and redundant geometric structures of 3D point cloud data. To address these challenges, we propose a new Incremental 3D Object Learning (i.e., I3DOL) model,…
C^2GR: Coupled Comprehensive Generative Replay for a Continually Learnable Universal Segmentation Model
Shanghai Jiao Tong University（上海交通大学）；Southeast University（东南大学）；Stevens Institute of Technology（史蒂文斯理工学院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Imperial College London（伦敦帝国学院）
Yonsei University（延世大学）；Korea Institute of Science and Technology (KIST)（韩国科学技术研究院）
Class-incremental semantic segmentation (CISS) labels each pixel of an image with a corresponding object/stuff class continually. To this end, it is crucial to learn novel classes incrementally without forgetting previously learned knowledge. Current CISS methods typically use a knowledge distillation (KD) technique for preserving classifier logits, or freeze a feature extractor, to avoid the forgetting problem. The strong constraints, however, prevent learning discriminative features for novel classes. We introduce a CISS framework that alleviates the forgetting problem and facilitates learni…
Suzhou University of Science and Technology（苏州科技大学）；Suzhou Institute of Trade & Commerce（苏州经贸职业技术学院）；Tianjin University（天津大学）；Jiangsu Industrial Intelligent and Low-carbon Technology Engineering Center（江苏省工业智能与低碳技术工程中心）；Suzhou Key Laboratory of Intelligent Low-carbon Technology Application（苏州市智能低碳技术应用重点实验室）
Few-shot class-incremental learning (FSCIL) aims to design machine learning algorithms that can continually learn new concepts from a few data points, without forgetting knowledge of old classes. The difficulty lies in that limited data from new classes not only lead to significant overfitting issues but also exacerbates the notorious catastrophic forgetting problems. However, existing FSCIL methods ignore the semantic relationships between sample-level and class-level. % Using the advantage that graph neural network (GNN) can mine rich information among few samples, In this paper, we designed…
Gradient-Semantic Compensation for Incremental Semantic Segmentation
Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）；Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences（中国科学院机器人与智能制造创新研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Nanyang Technological University（南洋理工大学）
Inception Institute of Artificial Intelligence（人工智能 inception 研究所）；University of California at Merced（加州大学默塞德分校）
In a conventional supervised learning setting, a machine learning model has access to examples of all object classes that are desired to be recognized during the inference stage. This results in a fixed model that lacks the flexibility to adapt to new learning tasks. In practical settings, learning tasks often arrive in a sequence and the models must continually learn to increment their previously acquired knowledge. Existing incremental learning approaches fall well below the state-of-the-art cumulative models that use all training classes at once. In this paper, we propose a random path sele…
External Knowledge Injection for CLIP-Based Class-Incremental Learning
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）
National University of Singapore（新加坡国立大学）；SIMTech, Agency for Science, Technology and Research（新加坡科学技术与研究局SIMTech研究所）；Hong Kong University of Science and Technology（香港科技大学）
This work focuses on tackling the challenging but realistic visual task of Incremental Few-Shot Learning (IFSL), which requires a model to continually learn novel classes from only a few examples while not forgetting the base classes on which it was pre-trained. Our study reveals that the challenges of IFSL lie in both inter-class separation and novel-class representation. Dur to intra-class variation, a novel class may implicitly leverage the knowledge from multiple base classes to construct its feature representation. Hence, simply reusing the pre-trained embedding space could lead to a scat…
