Recent Advances of Continual Learning in Computer Vision: An Overview

2021/09/23 by Haoxuan Qu, Qu, Haoxuan, Hossein Rahmani +7 · 11 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning and ELM #Multimodal Machine Learning Applications

paper · pdf · doi:10.48550/arxiv.2109.11369

openalex publication_date 2021/09/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In contrast to batch learning where all training data is available at once, continual learning represents a family of methods that accumulate knowledge and learn continuously with data available in sequential order. Similar to the human learning process with the ability of learning, fusing, and accumulating new knowledge coming at different time steps, continual learning is considered to have high practical significance. Hence, continual learning has been studied in various artificial intelligence tasks. In this paper, we present a comprehensive review of the recent progress of continual learning in computer vision. In particular, the works are grouped by their representative techniques, including regularization, knowledge distillation, memory, generative replay, parameter isolation, and a combination of the above techniques. For each category of these techniques, both its characteristics and applications in computer vision are presented. At the end of this overview, several subareas, where continuous knowledge accumulation is potentially helpful while continual learning has not been well studied, are discussed.

Citations

• Optimizing Neural Networks with Kronecker-factored Approximate Curvature
• Learning without Forgetting
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Generative replay with feedback connections as a general strategy for continual learning
• ContCap: A scalable framework for continual image captioning
• Coresets via Bilevel Optimization for Continual Learning and Streaming
• Graph-Based Continual Learning
• Wandering Within a World: Online Contextualized Few-Shot Learning
• Kernel Continual Learning

Cited by

• Rethinking Knowledge Distillation in Collaborative Machine Learning: Memory, Knowledge, and Their Interactions
• InvCoSS: Inversion-driven Continual Self-supervised Learning in Medical Multi-modal Image Pre-training
• Adversarial Pseudo-replay for Exemplar-free Class-incremental Learning
• Data Efficiency and Transfer Robustness in Biomedical Image Segmentation: A Study of Redundancy and Forgetting with Cellpose
• DRL: Discriminative Representation Learning with Parallel Adapters for Class Incremental Learning
• Channel Prediction under Network Distribution Shift Using Continual Learning-based Loss Regularization
• MEGG: Replay via Maximally Extreme GGscore in Incremental Learning for Neural Recommendation Models
• CRAM: Large-scale Video Continual Learning with Bootstrapped Compression
• UrbanMind: Towards Urban General Intelligence via Tool-Enhanced Retrieval-Augmented Generation and Multilevel Optimization
• Continual Speech Learning with Fused Speech Features
• Apax: A Flexible and Performant Framework For The Development of Machine-Learned Interatomic Potentials

Related

• CVPR 2020 Continual Learning in Computer Vision Competition: Approaches,\n Results, Current Challenges and Future Directions
• Toward Sustainable Continual Learning: Detection and Knowledge Repurposing of Similar Tasks
• Continual Learning in Human Activity Recognition: an Empirical Analysis of Regularization
• A Comprehensive Survey of Continual Learning: Theory, Method and Application
• A Closer Look at Rehearsal-Free Continual Learning