Forget but Recall: Incremental Latent Rectification in Continual Learning
원문 초록
Intrinsic capability to continuously learn a changing data stream is a desideratum of deep neural networks (DNNs). However, current DNNs suffer from catastrophic forgetting, which hinders remembering past knowledge. To mitigate this issue, existing Continual Learning (CL) approaches either retain exemplars for replay, regularize learning, or allocate dedicated capacity for new tasks. This paper investigates an unexplored CL direction for incremental learning called Incremental Latent Rectification or ILR. In a nutshell, ILR learns to propagate with correction (or rectify) the representation from the current trained DNN backward to the representation space of the old task, where performing predictive decisions is easier. This rectification process only employs a chain of small representation mapping networks, called rectifier units. Empirical experiments on several continual learning benchmarks, including CIFAR10, CIFAR100, and Tiny ImageNet, demonstrate the effectiveness and potential of this novel CL direction compared to existing representative CL methods.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts
CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning
PrePrompt: Predictive prompting for class incremental learning
LoRAX: LoRA eXpandable Networks for Continual Synthetic Image Attribution
IAP: Improving Continual Learning of Vision-Language Models via Instance-Aware Prompting
Do Your Best and Get Enough Rest for Continual Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.