Related references
Note: Only part of the references are listed.
Proceedings Paper
Computer Science, Artificial Intelligence
Leveraging Latent Features for Local Explanations
Ronny Luss et al.
Summary: This paper explores a new approach to explaining the decisions of deep neural networks by generating contrastive explanations using latent features. This method highlights aspects sufficient to justify classification and also introduces new aspects that can alter the classification.
KDD '21: PROCEEDINGS OF THE 27TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING (2021)
Review
Engineering, Multidisciplinary
A Survey on Contrastive Self-Supervised Learning
Ashish Jaiswal et al.
Summary: Self-supervised learning, particularly through contrastive learning, has gained popularity for its cost-effective approach in using self-defined pseudolabels for various downstream tasks. This paper extensively reviews self-supervised methods following the contrastive approach, explaining pretext tasks and different architectures used. Performance comparisons across multiple downstream tasks demonstrate variations in method effectiveness.
TECHNOLOGIES (2021)