Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Prithvijit Chattopadhyay"'
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585440
ECCV (9)
ECCV (9)
We introduce Domain-specific Masks for Generalization, a model for improving both in-domain and out-of-domain generalization performance. For domain generalization, the goal is to learn from a set of source domains to produce a single model that will
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::205214ed5d8b1c29013d4291ddec7e2f
https://doi.org/10.1007/978-3-030-58545-7_18
https://doi.org/10.1007/978-3-030-58545-7_18
Publikováno v:
Computer Vision – ECCV 2020 Workshops ISBN: 9783030664145
ECCV Workshops (1)
ECCV Workshops (1)
Convolutional Neural Networks have been shown to be vulnerable to adversarial examples, which are known to locate in subspaces close to where normal data lies but are not naturally occurring and of low probability. In this work, we investigate the po
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a418bd4d5f6f9e41ae64e5cd9c7eac9c
https://doi.org/10.1007/978-3-030-66415-2_3
https://doi.org/10.1007/978-3-030-66415-2_3
Publikováno v:
EMNLP/IJCNLP (1)
Prior work on training generative Visual Dialog models with reinforcement learning(Das et al.) has explored a Qbot-Abot image-guessing game and shown that this 'self-talk' approach can lead to improved performance at the downstream dialog-conditioned
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7612eeab747a818bc1f26a0d34dd969d
http://arxiv.org/abs/1909.10470
http://arxiv.org/abs/1909.10470
Publikováno v:
EMNLP
A rich line of research attempts to make deep neural networks more transparent by generating human-interpretable 'explanations' of their decision process, especially for interactive tasks like Visual Question Answering (VQA). In this work, we analyze
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6f167f0bb6255dd6f8a044f46942bc76
https://doi.org/10.18653/v1/d18-1128
https://doi.org/10.18653/v1/d18-1128
Autor:
Tilak Sharma, Ramprasaath R. Selvaraju, Devi Parikh, Prithvijit Chattopadhyay, Dhruv Batra, Mohamed Elhoseiny, Stefan Lee
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012601
ECCV (13)
ECCV (13)
Individual neurons in convolutional neural networks supervised for image-level classification tasks have been shown to implicitly learn semantically meaningful concepts ranging from simple textures and shapes to whole or partial objects – forming a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f6a071c0b555ecd38bd58c080aa93371
https://doi.org/10.1007/978-3-030-01261-8_32
https://doi.org/10.1007/978-3-030-01261-8_32