Latest Advancements Towards Catastrophic Forgetting under Data Scarcity: A Comprehensive Survey on Few-Shot Class Incremental Learning
Data scarcity significantly complicates the continual learning problem, i.e., how a deep neural network learns in dynamic environments with very few samples. However, the latest progress of few-shot class incremental learning (FSCIL) methods and related studies show insightful knowledge on how to tackle the problem. This paper presents a comprehensive survey on FSCIL that highlights several important aspects i.e. comprehensive and formal objectives of FSCIL approaches, the importance of prototype rectifications, the new learning paradigms based on pre-trained model and language-guided mechanism, the deeper analysis of FSCIL performance metrics and evaluation, and the practical contexts of FSCIL in various areas. Our extensive discussion presents the open challenges, potential solutions, and future directions of FSCIL.
Code (0)
등록된 구현이 없습니다.
Tasks
class-incremental learningClass Incremental LearningContinual LearningFew-Shot Class-Incremental LearningIncremental LearningSimilar Papers 제목 키워드 기반
Causes of Catastrophic Forgetting in Class-Incremental Semantic Segmentation
Class-incremental learning for semantic segmentation (CiSS) is presently a highly researched field which aims at updating a semantic segmentation model by sequentially learning new semantic classes. A major challenge in …
class-incremental learningClass Incremental LearningClass-Incremental Semantic SegmentationIncremental Learning+3Dissecting Catastrophic Forgetting in Continual Learning by Deep Visualization
Interpreting the behaviors of Deep Neural Networks (usually considered as a black box) is critical especially when they are now being widely adopted over diverse aspects of human life. Taking the advancements from Explai…
Continual LearningSelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment
Recent advancements in large language models (LLMs) have revolutionized natural language processing through their remarkable capabilities in understanding and executing diverse tasks. While supervised fine-tuning, partic…
Continual Learning with Pre-Trained Models: A Survey
Nowadays, real-world applications often face streaming data, which requires the learning system to absorb new knowledge as data evolves. Continual Learning (CL) aims to achieve this goal and meanwhile overcome the catast…
Continual LearningFairnessSurveyRobust Active Learning (RoAL): Countering Dynamic Adversaries in Active Learning with Elastic Weight Consolidation
Despite significant advancements in active learning and adversarial attacks, the intersection of these two fields remains underexplored, particularly in developing robust active learning frameworks against dynamic advers…
Active LearningAdversarial Attack