Pre-trained representation is one of the key elements in the success of modern deep learning. However, existing works on continual learning methods have mostly focused on learning models incrementally from scratch. In this paper, we explore an alternative framework to incremental learning where we continually fine-tune the model from a pre-trained representation. Our method takes advantage of linearization technique of a pre-trained neural network for simple and effective continual learning. We show that this allows us to design a linear model where quadratic parameter regularization method is placed as the optimal continual learning policy, and at the same time enjoying the high performance of neural networks. We also show that the proposed algorithm enables parameter regularization methods to be applied to class-incremental problems. Additionally, we provide a theoretical reason why the existing parameter-space regularization algorithms such as EWC underperform on neural networks trained with cross-entropy loss. We show that the proposed method can prevent forgetting while achieving high continual fine-tuning performance on image classification tasks. To show that our method can be applied to general continual learning settings, we evaluate our method in data-incremental, task-incremental, and class-incremental learning problems.
ICICLE: Interpretable Class Incremental Continual Learning
Jagiellonian University（雅盖隆大学）；Ardigen SA（阿迪根公司）；Autonomous University of Barcelona（巴塞罗那自治大学）；Computer Vision Center（计算机视觉中心）；IDEAS NCBR（IDEAS国家计算智能研究中心）
University of Pisa（比萨大学）；Scuola Normale Superiore（比萨高等师范学校）；University of Bologna（博洛尼亚大学）
The ability of a model to learn continually can be empirically assessed in different continual learning scenarios. Each scenario defines the constraints and the opportunities of the learning environment. Here, we challenge the current trend in the continual learning literature to experiment mainly on class-incremental scenarios, where classes present in one experience are never revisited. We posit that an excessive focus on this setting may be limiting for future research on continual learning, since class-incremental scenarios artificially exacerbate catastrophic forgetting, at the expense of…
GIST（光州科学技术院）；NAVER AI Lab（NAVER人工智能实验室）；Upstage AI Research（Upstage人工智能研究院）；Yonsei University（延世大学）
Despite rapid advances in continual learning, a large body of research is devoted to improving performance in the existing setups. While a handful of work do propose new continual learning setups, they still lack practicality in certain aspects. For better practicality, we first propose a novel continual learning setup that is online, task-free, class-incremental, of blurry task boundaries and subject to inference queries at any moment. We additionally propose a new metric to better measure the performance of the continual learning methods subject to inference queries at any moment. To address…
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）
Delft University of Technology（代尔夫特理工大学）；Brown University（布朗大学）
The human brain is capable of learning tasks sequentially mostly without forgetting. However, deep neural networks (DNNs) suffer from catastrophic forgetting when learning one task after another. We address this challenge considering a class-incremental learning scenario where the DNN sees test data without knowing the task from which this data originates. During training, Continual-Prune-and-Select (CP&S) finds a subnetwork within the DNN that is responsible for solving a given task. Then, during inference, CP&S selects the correct subnetwork to make predictions for that task. A new task is l…
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…
Modern machine learning systems need to be able to cope with constantly arriving and changing data. Two main areas of research dealing with such scenarios are continual learning and data stream mining. Continual learning focuses on accumulating knowledge and avoiding forgetting, assuming information once learned should be stored. Data stream mining focuses on adaptation to concept drift and discarding outdated information, assuming that only the most recent data is relevant. While these two areas are mainly being developed in separation, they offer complementary views on the problem of learnin…
Continual learning usually assumes the incoming data are fully labeled, which might not be applicable in real applications. In this work, we consider semi-supervised continual learning (SSCL) that incrementally learns from partially labeled data. Observing that existing continual learning methods lack the ability to continually exploit the unlabeled data, we propose deep Online Replay with Discriminator Consistency (ORDisCo) to interdependently learn a classifier with a conditional generative adversarial network (GAN), which continually passes the learned data distribution to the classifier. I…
Porsche Engineering Services GmbH（保时捷工程服务有限公司）；Fraunhofer IOSB（弗劳恩霍夫光学、系统技术与图像利用研究所）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
The field of continual deep learning is an emerging field and a lot of progress has been made. However, concurrently most of the approaches are only tested on the task of image classification, which is not relevant in the field of intelligent vehicles. Only recently approaches for class-incremental semantic segmentation were proposed. However, all of those approaches are based on some form of knowledge distillation. At the moment there are no investigations on replay-based approaches that are commonly used for object recognition in a continual setting. At the same time while unsupervised domai…
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…
Live and Learn: Continual Action Clustering with Incremental Views
School of Computer and Artificial Intelligence, Zhengzhou University（郑州大学计算机与人工智能学院）；School of Creative Technologies, University of Portsmouth（朴茨茅斯大学创意技术学院）
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）
Transfer learning is a powerful way to adapt existing deep learning models to new emerging use-cases in remote sensing. Starting from a neural network already trained for semantic segmentation, we propose to modify its label space to swiftly adapt it to new classes under weak supervision. To alleviate the background shift and the catastrophic forgetting problems inherent to this form of continual learning, we compare different regularization terms and leverage a pseudo-label strategy. We experimentally show the relevance of our approach on three public remote sensing datasets. Code is open-sou…
University of Cambridge（剑桥大学）；Binghamton University（宾汉姆顿大学）；Beijing University of Posts and Telecommunications（北京邮电大学）
As Facial Expression Recognition (FER) systems become integrated into our daily lives, these systems need to prioritise making fair decisions instead of aiming at higher individual accuracy scores. Ranging from surveillance systems to diagnosing mental and emotional health conditions of individuals, these systems need to balance the accuracy vs fairness trade-off to make decisions that do not unjustly discriminate against specific under-represented demographic groups. Identifying bias as a critical problem in facial analysis systems, different methods have been proposed that aim to mitigate bi…
Merge then Realign: Simple and Effective Modality-Incremental Continual Learning for Multimodal LLMs
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies（广东省新型安全智能技术重点实验室）
Few-Shot Domain Incremental Learning via Continual Vision-Language Consolidation
School of Computer Science and IT, Adelaide University, Australia（阿德莱德大学计算机科学与信息技术学院，澳大利亚）；Faculty of Engineering and IT, University of Technology Sydney (UTS), Australia（悉尼大学工程与信息技术学院（UTS），澳大利亚）；School of Artificial Intelligence and Computer Science, Nantong University, China（南通大学人工智能与计算机科学学院，中国）；College of Computing and Data Science, Nanyang Technological University, Singapore（南洋理工大学计算与数据科学学院，新加坡）
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…
Continual learning aims to learn new tasks incrementally using less computation and memory resources instead of retraining the model from scratch whenever new task arrives. However, existing approaches are designed in supervised fashion assuming all data from new tasks have been manually annotated, which are not practical for many real-life applications. In this work, we propose to use pseudo label instead of the ground truth to make continual learning feasible in unsupervised mode. The pseudo labels of new data are obtained by applying global clustering algorithm and we propose to use the mod…
Continual Instruction Tuning for Large Multimodal Models
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 Peng Cheng Laboratory（鹏城实验室）；Wuhan AI Research（武汉人工智能研究院）
Enhancing Generative Class Incremental Learning Performance with Model Forgetting Approach
Graduate School of Information Science and Technology, Hokkaido University（北海道大学信息科学与技术研究院）；Faculty of Information Science and Technology, Hokkaido University（北海道大学信息科学与技术学院）
PILOT: A Pre-Trained Model-Based Continual Learning Toolbox
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）
Nanyang Technological University（南洋理工大学）；University of South Australia（南澳大学）
Graph Neural Networks (GNNs) have become the backbone for a myriad of tasks pertaining to graphs and similar topological data structures. While many works have been established in domains related to node and graph classification/regression tasks, they mostly deal with a single task. Continual learning on graphs is largely unexplored and existing graph continual learning approaches are limited to the task-incremental learning scenarios. This paper proposes a graph continual learning strategy that combines the architecture-based and memory-based approaches. The structural learning strategy is dr…
Computer Aided Medical Procedures, Technische Universität München（慕尼黑工业大学计算机辅助医疗程序）；Canon Medical Research Europe ltd.（佳能医疗研究欧洲有限公司）；Computer Aided Medical Procedures, Johns Hopkins University, Baltimore, USA（约翰斯·霍普金斯大学计算机辅助医疗程序）
Deep learning organ segmentation approaches require large amounts of annotated training data, which is limited in supply due to reasons of confidentiality and the time required for expert manual annotation. Therefore, being able to train models incrementally without having access to previously used data is desirable. A common form of sequential training is fine tuning (FT). In this setting, a model learns a new task effectively, but loses performance on previously learned tasks. The Learning without Forgetting (LwF) approach addresses this issue via replaying its own prediction for past tasks …
Hierarchical-Task-Aware Multi-modal Mixture of Incremental LoRA Experts for Embodied Continual Learning
Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；Tsinghua University（清华大学）；Huazhong University of Science and Technology（华中科技大学）
The University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）
The staple of human intelligence is the capability of acquiring knowledge in a continuous fashion. In stark contrast, Deep Networks forget catastrophically and, for this reason, the sub-field of Class-Incremental Continual Learning fosters methods that learn a sequence of tasks incrementally, blending sequentially-gained knowledge into a comprehensive prediction. This work aims at assessing and overcoming the pitfalls of our previous proposal Dark Experience Replay (DER), a simple and effective approach that combines rehearsal and Knowledge Distillation. Inspired by the way our minds constantl…
University of Padova（帕多瓦大学）；Statwolf Data Science Srl（Statwolf数据科学公司）；Galdi Srl（加尔迪公司）
Continual Learning aims to learn from a stream of tasks, being able to remember at the same time both new and old tasks. While many approaches were proposed for single-class classification, multi-label classification in the continual scenario remains a challenging problem. For the first time, we study multi-label classification in the Domain Incremental Learning scenario. Moreover, we propose an efficient approach that has a logarithmic complexity with regard to the number of tasks, and can be applied also in the Class Incremental Learning scenario. We validate our approach on a real-world mul…
University of Amsterdam（阿姆斯特丹大学）；Inception Institute of Artificial Intelligence（Inception人工智能研究院）
Deep learning models have shown a great effectiveness in recognition of findings in medical images. However, they cannot handle the ever-changing clinical environment, bringing newly annotated medical data from different sources. To exploit the incoming streams of data, these models would benefit largely from sequentially learning from new samples, without forgetting the previously obtained knowledge. In this paper we introduce LifeLonger, a benchmark for continual disease classification on the MedMNIST collection, by applying existing state-of-the-art continual learning methods. In particular…
Peking University（北京大学）；South China University of Technology（华南理工大学）；National University of Singapore（新加坡国立大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
This paper studies a new, practical but challenging problem, called Class-Incremental Unsupervised Domain Adaptation (CI-UDA), where the labeled source domain contains all classes, but the classes in the unlabeled target domain increase sequentially. This problem is challenging due to two difficulties. First, source and target label sets are inconsistent at each time step, which makes it difficult to conduct accurate domain alignment. Second, previous target classes are unavailable in the current step, resulting in the forgetting of previous knowledge. To address this problem, we propose a nov…
Rochester Institute of Technology（罗切斯特理工学院）；Paige；Cornell Tech（康奈尔科技学院）
In continual learning, a system must incrementally learn from a non-stationary data stream without catastrophic forgetting. Recently, multiple methods have been devised for incrementally learning classes on large-scale image classification tasks, such as ImageNet. State-of-the-art continual learning methods use an initial supervised pre-training phase, in which the first 10% - 50% of the classes in a dataset are used to learn representations in an offline manner before continual learning of new classes begins. We hypothesize that self-supervised pre-training could yield features that generaliz…
University of São Paulo（圣保罗大学）；Eldorado Research Institute（埃尔多拉多研究所）
The field of Continual Learning investigates the ability to learn consecutive tasks without losing performance on those previously learned. Its focus has been mainly on incremental classification tasks. We believe that research in continual object detection deserves even more attention due to its vast range of applications in robotics and autonomous vehicles. This scenario is more complex than conventional classification given the occurrence of instances of classes that are unknown at the time, but can appear in subsequent tasks as a new class to be learned, resulting in missing annotations an…
