Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Vitali Petsiuk"'
Autor:
Sarah Adel Bargal, Andrea Zunino, Vitali Petsiuk, Jianming Zhang, Vittorio Murino, Stan Sclaroff, Kate Saenko
Publikováno v:
xxAI-Beyond Explainable AI ISBN: 9783031040825
Increased explainability in machine learning is traditionally associated with lower performance, e.g. a decision tree is more explainable, but less accurate than a deep neural network. We argue that, in fact, increasing the explainability of a deep c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::56522f7f8eddf6e30808ba3ebc3338eb
https://doi.org/10.1007/978-3-031-04083-2_13
https://doi.org/10.1007/978-3-031-04083-2_13
Autor:
Sarah Adel Bargal, Vittorio Murino, Kate Saenko, Vitali Petsiuk, Jianming Zhang, Andrea Zunino, Stan Sclaroff
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 43(11)
In state-of-the-art deep single-label classification models, the top- $k$ k $(k=2,3,4, \dots)$ ( k = 2 , 3 , 4 , ⋯ ) accuracy is usually significantly higher than the top-1 accuracy. This is more evident in fine-grained datasets, where differences
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6b1cf72bc0908b1afdd36e21f3c6da4e
https://pubmed.ncbi.nlm.nih.gov/33493111
https://pubmed.ncbi.nlm.nih.gov/33493111
Autor:
Vicente Ordonez, Vlad I. Morariu, Vitali Petsiuk, Kate Saenko, Rajiv Jain, Ashutosh Mehra, Varun Manjunatha
Publikováno v:
CVPR
We propose D-RISE, a method for generating visual explanations for the predictions of object detectors. Utilizing the proposed similarity metric that accounts for both localization and categorization aspects of object detection allows our method to p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6b558970d247c43187d73014b1cc515c
http://arxiv.org/abs/2006.03204
http://arxiv.org/abs/2006.03204
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030586201
ECCV (11)
ECCV (11)
Explaining a deep learning model can help users understand its behavior and allow researchers to discern its shortcomings. Recent work has primarily focused on explaining models for tasks like image classification or visual question answering. In thi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9686b599f7625af8b77e308771a66068
https://doi.org/10.1007/978-3-030-58621-8
https://doi.org/10.1007/978-3-030-58621-8
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030586201
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::767a8547530227336ddde74a48fc03f0
https://doi.org/10.1007/978-3-030-58621-8_38
https://doi.org/10.1007/978-3-030-58621-8_38