Class incremental learning for video action classification
원문 초록
Class Incremental Learning (CIL) is a hot topic in machine learning for CNN models to learn new classes incrementally. However, most of the CIL studies are for image classification and object recognition tasks and few CIL studies are available for video action classification. To mitigate this problem, in this paper, we present a new Grow When Required network (GWR) based video CIL framework for action classification. GWR learns knowledge incrementally by modeling the manifold of video frames for each encountered action class in feature space. We also introduce a Knowledge Consolidation (KC) method to separate the feature manifolds of old class and new class and introduce an associative matrix for label prediction. Experimental results on KTH and Weizmann demonstrate the effectiveness of the framework.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning
The Bayesian Approach to Continual Learning: An Overview
Listen, Analyze, and Adapt to Learn New Attacks: An Exemplar-Free Class Incremental Learning Method for Audio Deepfake Source Tracing
Helpful or Harmful: Inter-Task Association in Continual Learning
MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos
Support Vector Machines with Time Series Distance Kernels for Action Classification
토론
이 논문과 연결된 포럼 글이 아직 없습니다.