Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Vo, Huy V."'
Autor:
Vo, Huy V., Khalidov, Vasil, Darcet, Timothée, Moutakanni, Théo, Smetanin, Nikita, Szafraniec, Marc, Touvron, Hugo, Couprie, Camille, Oquab, Maxime, Joulin, Armand, Jégou, Hervé, Labatut, Patrick, Bojanowski, Piotr
Self-supervised features are the cornerstone of modern machine learning systems. They are typically pre-trained on data collections whose construction and curation typically require extensive human effort. This manual process has some limitations sim
Externí odkaz:
http://arxiv.org/abs/2405.15613
Autor:
Sizikova, Elena, Vendrow, Joshua, Cao, Xu, Grotheer, Rachel, Haddock, Jamie, Kassab, Lara, Kryshchenko, Alona, Merkh, Thomas, Madushani, R. W. M. A., Moise, Kenny, Ulichney, Annie, Vo, Huy V., Wang, Chuntian, Coffee, Megan, Leonard, Kathryn, Needell, Deanna
Automatic infectious disease classification from images can facilitate needed medical diagnoses. Such an approach can identify diseases, like tuberculosis, which remain under-diagnosed due to resource constraints and also novel and emerging diseases,
Externí odkaz:
http://arxiv.org/abs/2209.02415
Object detectors trained with weak annotations are affordable alternatives to fully-supervised counterparts. However, there is still a significant performance gap between them. We propose to narrow this gap by fine-tuning a base pre-trained weakly-su
Externí odkaz:
http://arxiv.org/abs/2207.12112
Autor:
Siméoni, Oriane, Puy, Gilles, Vo, Huy V., Roburin, Simon, Gidaris, Spyros, Bursuc, Andrei, Pérez, Patrick, Marlet, Renaud, Ponce, Jean
Publikováno v:
BMVC 2021
Localizing objects in image collections without supervision can help to avoid expensive annotation campaigns. We propose a simple approach to this problem, that leverages the activation features of a vision transformer pre-trained in a self-supervise
Externí odkaz:
http://arxiv.org/abs/2109.14279
Existing approaches to unsupervised object discovery (UOD) do not scale up to large datasets without approximations that compromise their performance. We propose a novel formulation of UOD as a ranking problem, amenable to the arsenal of distributed
Externí odkaz:
http://arxiv.org/abs/2106.06650
Autor:
Tolan, Jamie, Yang, Hung-I, Nosarzewski, Benjamin, Couairon, Guillaume, Vo, Huy V., Brandt, John, Spore, Justine, Majumdar, Sayantan, Haziza, Daniel, Vamaraju, Janaki, Moutakanni, Theo, Bojanowski, Piotr, Johns, Tracy, White, Brian, Tiecke, Tobias, Couprie, Camille
Publikováno v:
In Remote Sensing of Environment 1 January 2024 300
This paper addresses the problem of discovering the objects present in a collection of images without any supervision. We build on the optimization approach of Vo et al. (CVPR'19) with several key novelties: (1) We propose a novel saliency-based regi
Externí odkaz:
http://arxiv.org/abs/2007.02662
Learning with complete or partial supervision is powerful but relies on ever-growing human annotation efforts. As a way to mitigate this serious problem, as well as to serve specific applications, unsupervised learning has emerged as an important fie
Externí odkaz:
http://arxiv.org/abs/1904.03148
Scene-agnostic visual inpainting remains very challenging despite progress in patch-based methods. Recently, Pathak et al. 2016 have introduced convolutional "context encoders" (CEs) for unsupervised feature learning through image completion tasks. W
Externí odkaz:
http://arxiv.org/abs/1803.10348
Autor:
Vo, Huy V.
Publikováno v:
Artificial Intelligence [cs.AI]. Ecole normale supérieure-ENS PARIS, 2022. English. ⟨NNT : ⟩
Object detectors are important components of intelligent systems such as autonomous vehicles or robots. They are typically obtained with fully-supervised training, which requires large manually annotated datasets whose construction is time-consuming
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::ee289958c174b074858fb50da92dadbc
https://hal.science/tel-03919952
https://hal.science/tel-03919952