Knowledge Adaptation Network for Few-Shot Class-Incremental Learning
Few-shot class-incremental learning (FSCIL) aims to incrementally recognize new classes using a few samples while maintaining the performance on previously learned classes. One of the effective methods to solve this challenge is to construct prototypical evolution classifiers. Despite the advancement achieved by most existing methods, the classifier weights are simply initialized using mean features. Because representations for new classes are weak and biased, we argue such a strategy is suboptimal. In this paper, we tackle this issue from two aspects. Firstly, thanks to the development of foundation models, we employ a foundation model, the CLIP, as the network pedestal to provide a general representation for each class. Secondly, to generate a more reliable and comprehensive instance representation, we propose a Knowledge Adapter (KA) module that summarizes the data-specific knowledge from training data and fuses it into the general representation. Additionally, to tune the knowledge learned from the base classes to the upcoming classes, we propose a mechanism of Incremental Pseudo Episode Learning (IPEL) by simulating the actual FSCIL. Taken together, our proposed method, dubbed as Knowledge Adaptation Network (KANet), achieves competitive performance on a wide range of datasets, including CIFAR100, CUB200, and ImageNet-R.
Code (0)
등록된 구현이 없습니다.
Tasks
class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
MgSvF: Multi-Grained Slow vs. Fast Framework for Few-Shot Class-Incremental Learning
As a challenging problem, few-shot class-incremental learning (FSCIL) continually learns a sequence of tasks, confronting the dilemma between slow forgetting of old knowledge and fast adaptation to new knowledge. In this…
class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental LearningA Strong Baseline for Semi-Supervised Incremental Few-Shot Learning
Few-shot learning (FSL) aims to learn models that generalize to novel classes with limited training samples. Recent works advance FSL towards a scenario where unlabeled examples are also available and propose semi-superv…
Few-Shot LearningAnchorInv: Few-Shot Class-Incremental Learning of Physiological Signals via Representation Space Guided Inversion
Deep learning models have demonstrated exceptional performance in a variety of real-world applications. These successes are often attributed to strong base models that can generalize to novel tasks with limited supportin…
class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental LearningFew-shot Class-variable Incremental Audio Classification via Prototype Adaptation and Pseudo Class-variable Training
In the task of few-shot class-incremental audio classification, the number of classes is assumed to always increase without considering the possibility of decrease. However, the number of classes generally increases or d…
Audio ClassificationClass-Incremental Few-Shot Event Detection
Event detection is one of the fundamental tasks in information extraction and knowledge graph. However, a realistic event detection system often needs to deal with new event classes constantly. These new classes usually …
Event DetectionFew-Shot LearningKnowledge DistillationPrompt Learning