Abstract
Active learning(AL) has recently gained popularity for deep learning(DL) models. This is due to efficient and informative sampling, especially when the learner requires large-scale labelled datasets. Commonly, the sampling and training happen in stages while more batches are added. One main bottleneck in this strategy is the narrow representation learned by the model that affects the overall AL selection. We present MoBYv2AL, a novel self-supervised active learning framework for image classification. Our contribution lies in lifting MoBY -- one of the most successful self-supervised learning algorithms to the AL pipeline. Thus, we add the downstream task-aware objective function and optimize it jointly with contrastive loss. Further, we derive a data-distribution selection function from labelling the new examples. Finally, we test and study our pipeline robustness and performance for image classification tasks. We successfully achieved state-of-the-art results when compared to recent AL methods.
Original language | English |
---|---|
Title of host publication | 33rd British Machine Vision Conference 2022 |
Subtitle of host publication | (BMVC) 2022, London, UK, November 21-24, 2022 |
Publisher | BMVA |
Number of pages | 13 |
DOIs | |
Publication status | Published - 24 Nov 2022 |
Externally published | Yes |
Event | The 33rd British Machine Vision Conference - London, United Kingdom Duration: 21 Nov 2022 → 24 Nov 2022 https://bmvc2022.org/ |
Conference
Conference | The 33rd British Machine Vision Conference |
---|---|
Abbreviated title | BMVC 2022 |
Country/Territory | United Kingdom |
City | London |
Period | 21/11/22 → 24/11/22 |
Internet address |