DSS: A Diverse Sample Selection Method to Preserve Knowledge in Class-Incremental Learning
Rehearsal-based techniques are commonly used to mitigate catastrophic forgetting (CF) in Incremental learning (IL). The quality of the exemplars selected is important for this purpose and most methods do not ensure the appropriate diversity of the selected exemplars. We propose a new technique "DSS" -- Diverse Selection of Samples from the input data stream in the Class-incremental learning (CIL) setup under both disjoint and fuzzy task boundary scenarios. Our method outperforms state-of-the-art methods and is much simpler to understand and implement.
Code (0)
등록된 구현이 없습니다.
Tasks
class-incremental learningClass Incremental LearningDiversityIncremental LearningSimilar Papers 제목 키워드 기반
MECAD: A multi-expert architecture for continual anomaly detection
In this paper we propose MECAD, a novel approach for continual anomaly detection using a multi-expert architecture. Our system dynamically assigns experts to object classes based on feature similarity and employs efficie…
Computational EfficiencyIncremental LearningAnomaly DetectionRehearsal with Auxiliary-Informed Sampling for Audio Deepfake Detection
The performance of existing audio deepfake detection frameworks degrades when confronted with new deepfake attacks. Rehearsal-based continual learning (CL), which updates models using a limited set of old data samples, h…
Audio Deepfake DetectionContinual LearningDeepFake DetectionDiversity+1Fine-Grained Knowledge Selection and Restoration for Non-Exemplar Class Incremental Learning
Non-exemplar class incremental learning aims to learn both the new and old tasks without accessing any training data from the past. This strict restriction enlarges the difficulty of alleviating catastrophic forgetting s…
class-incremental learningClass Incremental LearningIncremental LearningKnowledge DistillationEnhancing Knowledge Selection for Grounded Dialogues via Document Semantic Graphs
Providing conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging. Existing models treat knowledge selection as a sentence ranking or classification proble…
Multi-Task LearningResponse GenerationSentencePersonaEdit: Representative Sample Selection for Personalized Model Editing
Personalization has attracted growing interest in LLM applications, yet existing retrieval-based approaches depend heavily on retrieval quality and degrade in long-term interactions. Model editing, which directly modifie…
knowledge editing