|
ИСТИНА |
Войти в систему Регистрация |
ИСТИНА ЦЭМИ РАН |
||
TETRIS: Towards Exploring the Robustness of Interactive Segmentationстатья
Информация о цитировании статьи получена из
Scopus
Дата последнего поиска статьи во внешних источниках: 15 мая 2024 г.
- Авторы: Moskalenko Andrey, Shakhuro Vlad, Vorontsova Anna, Konushin Anton, Antonov Anton, Krapukhin Alexander, Shepelev Denis, Soshin Konstantin
- Сборник: Proceedings of the AAAI Conference on Artificial Intelligence
- Том: 38
- Год издания: 2024
- Издательство: American Association for Artificial Intelligence (AAAI) Press
- Местоположение издательства: United States
- Первая страница: 4287
- Последняя страница: 4295
- DOI: 10.1609/aaai.v38i5.28225
- Аннотация: Interactive segmentation methods rely on user inputs to iteratively update the selection mask. A click specifying the object of interest is arguably the most simple and intuitive interaction type, and thereby the most common choice for interactive segmentation. However, user clicking patterns in the interactive segmentation context remain unexplored. Accordingly, interactive segmentation evaluation strategies rely more on intuition and common sense rather than empirical studies (e.g., assuming that users tend to click in the center of the area with the largest error). In this work, we conduct a real-user study to investigate real user clicking patterns. This study reveals that the intuitive assumption made in the common evaluation strategy may not hold. As a result, interactive segmentation models may show high scores in the standard benchmarks, but it does not imply that they would perform well in a real world scenario. To assess the applicability of interactive segmentation methods, we propose a novel evaluation strategy providing a more comprehensive analysis of a model's performance. To this end, we propose a methodology for finding extreme user inputs by a direct optimization in a white-box adversarial attack on the interactive segmentation model. Based on the performance with such adversarial user inputs, we assess the robustness of interactive segmentation models w.r.t click positions. Besides, we introduce a novel benchmark for measuring the robustness of interactive segmentation, and report the results of an extensive evaluation of dozens of models.
- Добавил в систему: Москаленко Андрей Викторович
Прикрепленные файлы
| № | Имя | Описание | Имя файла | Размер | Добавлен |
|---|---|---|---|---|---|
| 1. | Полный текст | TETRIS.pdf | 16,5 МБ | 27 марта 2024 [MoskalenkoAV] | |
| 2. | Результаты экспериментов | TETRIS.zip | 151,9 КБ | 27 марта 2024 [MoskalenkoAV] |