홈 › Papers

Learning a Condensed Frame for Memory-Efficient Video Class-Incremental Learning

2022-11-02 · Yixuan Pei, Zhiwu Qing, Jun Cen, Xiang Wang, Shiwei Zhang, Yaxiong Wang, Mingqian Tang, Nong Sang, Xueming Qian

Recent incremental learning for action recognition usually stores representative videos to mitigate catastrophic forgetting. However, only a few bulky videos can be stored due to the limited memory. To address this problem, we propose FrameMaker, a memory-efficient video class-incremental learning approach that learns to produce a condensed frame for each selected video. Specifically, FrameMaker is mainly composed of two crucial components: Frame Condensing and Instance-Specific Prompt. The former is to reduce the memory cost by preserving only one condensed frame instead of the whole video, while the latter aims to compensate the lost spatio-temporal details in the Frame Condensing stage. By this means, FrameMaker enables a remarkable reduction in memory but keep enough information that can be applied to following incremental tasks. Experimental results on multiple challenging benchmarks, i.e., HMDB51, UCF101 and Something-Something V2, demonstrate that FrameMaker can achieve better performance to recent advanced methods while consuming only 20% memory. Additionally, under the same memory consumption conditions, FrameMaker significantly outperforms existing state-of-the-arts by a convincing margin.

📄 PDF Abstract BibTeX arXiv:2211.00833

Code (0)

등록된 구현이 없습니다.

Tasks

Action Recognition class-incremental learning Class Incremental Learning Incremental Learning

Condensed Prototype Replay for Class Incremental Learning

2023-05-25 · Jiangtao Kong, Zhenyu Zong, Tianyi Zhou, Huajie Shao

Incremental learning (IL) suffers from catastrophic forgetting of old tasks when learning new tasks. This can be addressed by replaying previous tasks' data stored in a memory, which however is usually prone to size limi…

class-incremental learning Class Incremental Learning Incremental Learning

CD^2: Constrained Dataset Distillation for Few-Shot Class-Incremental Learning

2026-01-13 · Kexin Bao, Daichi Zhang, Hansong Zhang, Yong Li 외 arxiv

Few-shot class-incremental learning (FSCIL) receives significant attention from the public to perform classification continuously with a few training samples, which suffers from the key catastrophic forgetting problem. E…

Few-Shot Class-Incremental Learning

TokensGen: Harnessing Condensed Tokens for Long Video Generation

2025-07-21 · Wenqi Ouyang, Zeqi Xiao, Danni Yang, Yifan Zhou 외 arxiv

Generating consistent long videos is a complex challenge: while diffusion-based generative models generate visually impressive short clips, extending them to longer durations often leads to memory bottlenecks and long-te…

Video Generation

Slightly Shift New Classes to Remember Old Classes for Video Class-Incremental Learning

2024-04-01 · Jian Jiao, Yu Dai, Hefei Mei, Heqian Qiu 외

Recent video class-incremental learning usually excessively pursues the accuracy of the newly seen classes and relies on memory sets to mitigate catastrophic forgetting of the old classes. However, limited storage only a…

class-incremental learning Class Incremental Learning Incremental Learning

ESSENTIAL: Episodic and Semantic Memory Integration for Video Class-Incremental Learning

2025-08-14 · Jongseo Lee, Kyungho Bae, Kyle Min, Gyeong-Moon Park 외 arxiv

In this work, we tackle the problem of video classincremental learning (VCIL). Many existing VCIL methods mitigate catastrophic forgetting by rehearsal training with a few temporally dense samples stored in episodic memo…

class-incremental learning General Knowledge