FOCAL: A Cost-Aware Video Dataset for Active Learning

[PDF] arxiv.org

Targeting Negative Flips in Active Learning using Validation Sets

R Benkert, M Prabhushankar, G AlRegib - arXiv preprint arXiv:2411.10896, 2024 - arxiv.org
The performance of active learning algorithms can be improved in two ways. The often used
and intuitive way is by reducing the overall error rate within the test set. The second way is to …
相关文章 所有 2 个版本
[PDF] arxiv.org

Explaining Representation Learning with Perceptual Components

Y Yarici, K Kokilepersaud, M Prabhushankar… - arXiv preprint arXiv …, 2024 - arxiv.org
Self-supervised models create representation spaces that lack clear semantic meaning. This
interpretability problem of representations makes traditional explainability methods …
相关文章 所有 2 个版本