Visual Probing: Cognitive Framework for Explaining Self-Supervised Image Representations
Recently introduced self-supervised methods for image representation learning provide on par or superior results to their fully supervised competitors, yet the corresponding efforts to explain the self-supervised approaches lag behind. Motivated by this observation, we introduce a novel visual probi...
Main Authors: | Witold Oleszkiewicz, Dominika Basaj, Igor Sieradzki, Micha Gorszczak, Barbara Rychalska, Koryna Lewandowska, Tomasz Trzcinski, Bartosz Zielinski |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10038644/ |
Similar Items
-
Robust and Explainable Semi-Supervised Deep Learning Model for Anomaly Detection in Aviation
by: Milad Memarzadeh, et al.
Published: (2022-08-01) -
Weakly supervised segmentation models as explainable radiological classifiers for lung tumour detection on CT images
by: Robert O’Shea, et al.
Published: (2023-11-01) -
ExpPoint-MAE: Better Interpretability and Performance for Self-Supervised Point Cloud Transformers
by: Ioannis Romanelis, et al.
Published: (2024-01-01) -
Relevance maps: A weakly supervised segmentation method for 3D brain tumours in MRIs
by: Sajith Rajapaksa, et al.
Published: (2022-12-01) -
Competency-based mental health supervision: evidence-based tool needs for the humanitarian context
by: Bettina Böhm, et al.
Published: (2022-01-01)