Autor: Basaj, Dominika - Prolib Integro

Skocz do pozycji: 1.

Tytuł:: Which visual features impact the performance of target task in self-supervised learning?
Autorzy:: Oleszkiewicz, Witold
Zieliński, Bartosz
Basaj, Dominika
Trzciński, Tomasz
Wydawca:: Springer
Dostawca treści:: Repozytorium Uniwersytetu Jagiellońskiego

Inne

na półce

Skocz do pozycji: 2.

Tytuł:: Explaining self-supervised image representations with visual probing
Autorzy:: Oleszkiewicz, Witold
Zieliński, Bartosz
Sieradzki, Igor
Basaj, Dominika
Rychalska, Barbara
Trzciński, Tomasz
Górszczak, Michał
Wydawca:: International Joint Conferences on Artificial Intelligence
Opis:: 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 probing framework for explaining the self-supervised models by leveraging probing tasks employed previously in natural language processing. The probing tasks require knowledge about semantic relationships between image parts. Hence, we propose a systematic approach to obtain analogs of natural language in vision, such as visual words, context, and taxonomy. We show the effectiveness and applicability of those analogs in the context of explaining self-supervised representations. Our key findings emphasize that relations between language and vision can serve as an effective yet intuitive tool for discovering how machine learning models work, independently of data modality. Our work opens a plethora of research pathways towards more explainable and transparent AI.
Dostawca treści:: Repozytorium Uniwersytetu Jagiellońskiego

Inne

na półce

Skocz do pozycji: 3.

Tytuł:: Visual probing : cognitive framework for explaining self-supervised image representations
Autorzy:: Oleszkiewicz, Witold
Trzciński, Tomasz
Zieliński, Bartosz
Sieradzki, Igor
Rychalska, Barbara
Basaj, Dominika
Lewandowska, Koryna
Górszczak, Michał
Opis:: 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 probing framework for explaining the self-supervised models by leveraging probing tasks employed previously in natural language processing. The probing tasks require knowledge about semantic relationships between image parts. Hence, we propose a systematic approach to obtain analogs of natural language in vision, such as visual words, context, and taxonomy. Our proposal is grounded in Marr’s computational theory of vision and concerns features like textures, shapes, and lines. We show the effectiveness and applicability of those analogs in the context of explaining self-supervised representations. Our key findings emphasize that relations between language and vision can serve as an effective yet intuitive tool for discovering how machine learning models work, independently of data modality. Our work opens a plethora of research pathways towards more explainable and transparent AI.
Dostawca treści:: Repozytorium Uniwersytetu Jagiellońskiego

Artykuł

na półce

Informacja

Wyszukujesz frazę "Basaj, Dominika" wg kryterium: Autor