International Workshop on Continual Semi-Supervised Learning: Introduction, Benchmarks and Baselines
원문 초록
The aim of this paper is to formalize a new continual semi-supervised learning (CSSL) paradigm, proposed to the attention of the machine learning community via the IJCAI 2021 International Workshop on Continual Semi-Supervised Learning (CSSL-IJCAI), with the aim of raising field awareness about this problem and mobilizing its effort in this direction. After a formal definition of continual semi-supervised learning and the appropriate training and testing protocols, the paper introduces two new benchmarks specifically designed to assess CSSL on two important computer vision tasks: activity recognition and crowd counting. We describe the Continual Activity Recognition (CAR) and Continual Crowd Counting (CCC) challenges built upon those benchmarks, the baseline models proposed for the challenges, and describe a simple CSSL baseline which consists in applying batch self-training in temporal sessions, for a limited number of rounds. The results show that learning from unlabelled data streams is extremely challenging, and stimulate the search for methods that can encode the dynamics of the data stream.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
OmniFall: From Staged Through Synthetic to Wild, A Unified Multi-Domain Dataset for Robust Fall Detection
Car Object Counting and Position Estimation via Extension of the CLIP-EBC Framework
SEZ-HARN: Self-Explainable Zero-shot Human Activity Recognition Network
EBC-ZIP: Improving Blockwise Crowd Counting with Zero-Inflated Poisson Regression
Through-the-Wall Radar Human Activity Recognition WITHOUT Using Neural Networks
Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting
토론
이 논문과 연결된 포럼 글이 아직 없습니다.