← Search

Michał Górszczak

2 accepted papers

2022

Interpretable Image Classification with Differentiable Prototypes Assignment

ECCV 2022poster

"Existing prototypical-based models address the black-box nature of deep learning. However, they are sub-optimal as they often assume separate prototypes for each class, require multi-step optimization, make decisions based on prototype absence (so-called negative reasoning process), and derive vagu…

2021

Explaining Self-Supervised Image Representations with Visual Probing

IJCAI 2021poster

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…