paper-with-me

Papers

vCLIMB: A Novel Video Class Incremental Learning Benchmark

2022-01-23 · CVPR 2022 1 · Andrés Villa, Kumail Alhamoud, Juan León Alcázar, Fabian Caba Heilbron, Victor Escorcia, Bernard Ghanem

Continual learning (CL) is under-explored in the video domain. The few existing works contain splits with imbalanced class distributions over the tasks, or study the problem in unsuitable datasets. We introduce vCLIMB, a novel video continual learning benchmark. vCLIMB is a standardized test-bed to analyze catastrophic forgetting of deep models in video continual learning. In contrast to previous work, we focus on class incremental continual learning with models trained on a sequence of disjoint tasks, and distribute the number of classes uniformly across the tasks. We perform in-depth evaluations of existing CL methods in vCLIMB, and observe two unique challenges in video data. The selection of instances to store in episodic memory is performed at the frame level. Second, untrimmed training data influences the effectiveness of frame sampling strategies. We address these two challenges by proposing a temporal consistency regularization that can be applied on top of memory-based continual learning methods. Our approach significantly improves the baseline, by up to 24% on the untrimmed continual learning task.

📄 PDF Abstract BibTeX arXiv:2201.09381

Code (0)

등록된 구현이 없습니다.

Tasks

class-incremental learningClass Incremental LearningContinual LearningIncremental Learning

Similar Papers 제목 키워드 기반

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 learningGeneral Knowledge

When Video Classification Meets Incremental Classes

2021-06-30 · Hanbin Zhao, Xin Qin, Shihao Su, Yongjian Fu 외

With the rapid development of social media, tremendous videos with new classes are generated daily, which raise an urgent demand for video classification methods that can continuously update new classes while maintaining…

Classificationclass-incremental learningClass Incremental LearningIncremental Learning+2

Learning Conditional Space-Time Prompt Distributions for Video Class-Incremental Learning

2025-01-01 · CVPR 2025 1 · Xiaohan Zou, Wenchao Ma, Shu Zhao

Recent advancements in prompt-based learning have significantly advanced image and video class-incremental learning. However, the prompts learned by these methods often fail to capture the diverse and informative cha…

class-incremental learningClass Incremental LearningIncremental LearningPrompt Learning

Video Domain Incremental Learning for Human Action Recognition in Home Environments

2024-12-22 · Yuanda Hu, Xing Liu, Meiying Li, Yate Ge 외

It is significantly challenging to recognize daily human actions in homes due to the diversity and dynamic changes in unconstrained home environments. It spurs the need to continually adapt to various users and scenes. F…

Action Recognitionclass-incremental learningClass Incremental LearningContinual Learning+3

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

2022-11-02 · Yixuan Pei, Zhiwu Qing, Jun Cen, Xiang Wang 외

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 probl…

Action Recognitionclass-incremental learningClass Incremental LearningIncremental Learning