DeepAI AI Chat
Log In Sign Up

International Workshop on Continual Semi-Supervised Learning: Introduction, Benchmarks and Baselines

by   Ajmal Shahbaz, et al.
HUAWEI Technologies Co., Ltd.
Oxford Brookes University
University of Pisa

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.


page 1

page 2

page 3

page 4


Hypernetworks for Continual Semi-Supervised Learning

Learning from data sequentially arriving, possibly in a non i.i.d. way, ...

S4-Crowd: Semi-Supervised Learning with Self-Supervised Regularisation for Crowd Counting

Crowd counting has drawn more attention because of its wide application ...

A soft nearest-neighbor framework for continual semi-supervised learning

Despite significant advances, the performance of state-of-the-art contin...

Semi-Supervised Learning with Multi-Head Co-Training

Co-training, extended from self-training, is one of the frameworks for s...

Distributionally Robust Semi-Supervised Learning for People-Centric Sensing

Semi-supervised learning is crucial for alleviating labelling burdens in...

The CLEAR Benchmark: Continual LEArning on Real-World Imagery

Continual learning (CL) is widely regarded as crucial challenge for life...