Continual Learning

Follow this topic Ask about this topic

Continual Learning studies how models adapt to sequences of tasks or non-stationary data without losing useful earlier knowledge, a challenge known as catastrophic forgetting. Common approaches replay selected examples, regularize updates to protect important parameters, isolate tasks with adapters or separate subnetworks, or manage knowledge through prompts, memory, and model expansion. Methods are tested on class- and domain-incremental image benchmarks such as CIFAR and ImageNet, as well as task-free streams and applications in language, robotics, and healthcare. A central tension is balancing retention with the capacity to learn, while evaluations increasingly question assumptions such as known task boundaries and seek to measure transfer, recovery, resource use, and performance under realistic shifts.

Latest papers

301 papers35 papers in the last four weeks, up 84% on the four weeks before. 0.2% of all new papers.

CMFDFormer: Transformer-based Copy-Move Forgery Detection with Continual Learning
Nov 22, 2023Yaqi Liu, Chao Xia, Song Xiao +4Image Forgery Detection Image Forgery Localization
Beijing Electronic Science and Technology Institute, Beijing 100070, China · the Computer Engineering College, Jimei University, Xiamen 361021, China · the State Key Laboratory of Integrated Service Network, Xidian University, Xi’an 710071, China +1

Nov 22, 2023J/K move · Enter open · S save

CMFDFormer: Transformer-based Copy-Move Forgery Detection with Continual Learning

Yaqi Liu, Chao Xia, Song Xiao, Qingxiao Guan+3

Beijing Electronic Science and Technology Institute, Beijing 100070, China · the Computer Engineering College, Jimei University, Xiamen 361021, China · the State Key Laboratory of Integrated Service Network, Xidian University, Xi’an 710071, China+1

Image Forgery Detection Image Forgery Localization Continual Learning

Open paper AskPDF arXiv

Copy-move forgery detection aims at detecting duplicated regions in a suspected forged image, and deep learning based copy-move forgery detection methods are in the ascendant. These deep learning based methods heavily rely on synthetic training data, and the performance will degrade when facing new tasks. In this paper, we propose a Transformer-style copy-move forgery detection network named as CMFDFormer, and provide a novel PCSD (Pooled Cube and Strip Distillation) continual learning framework to help CMFDFormer handle new tasks. CMFDFormer consists of a MiT (Mix Transformer) backbone network and a PHD (Pluggable Hybrid Decoder) mask prediction network. The MiT backbone network is a Transformer-style network which is adopted on the basis of comprehensive analyses with CNN-style and MLP-style backbones. The PHD network is constructed based on self-correlation computation, hierarchical feature integration, a multi-scale cycle fully-connected block and a mask reconstruction block. The PHD network is applicable to feature extractors of different styles for hierarchical multi-scale information extraction, achieving comparable performance. Last but not least, we propose a PCSD continual learning framework to improve the forgery detectability and avoid catastrophic forgetting when handling new tasks. Our continual learning framework restricts intermediate features from the PHD network, and takes advantage of both cube pooling and strip pooling. Extensive experiments on publicly available datasets demonstrate the good performance of CMFDFormer and the effectiveness of the PCSD continual learning framework.