Active Learning Strategies for Weakly-Supervised Object Detection

Autor: Huy V. Vo, Oriane Siméoni, Spyros Gidaris, Andrei Bursuc, Patrick Pérez, Jean Ponce

Publikováno v: Lecture Notes in Computer Science ISBN: 9783031200557

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::1ff3f8435dcad03478abe9e93444ca3f
https://doi.org/10.1007/978-3-031-20056-4_13

Rethinking deep active learning: Using unlabeled data at model training

Autor: Oriane Siméoni, Yannis Avrithis, Guillaume Gravier, Mateusz Budnik

Publikováno v: ICPR 2020-25th International Conference on Pattern Recognition
ICPR 2020-25th International Conference on Pattern Recognition, Jan 2021, Milan, Italy. pp.1-12
International Conference on Pattern Recognition
International Conference on Pattern Recognition, 2020, Milan, Italy
ICPR

International audience; Active learning typically focuses on training a model on few labeled examples alone, while unlabeled ones are only used for acquisition. In this work we depart from this setting by using both labeled and unlabeled data during

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::12e0a0266c90869a4299232993c0d8b9
https://inria.hal.science/hal-02372102

Unsupervised object discovery for instance recognition

Autor: Oriane Siméoni, Ondrej Chum, Giorgos Tolias, Yannis Avrithis, Ahmet Iscen

Publikováno v: WACV
WACV 2018-IEEE Winter Conference on Applications of Computer Vision
WACV 2018-IEEE Winter Conference on Applications of Computer Vision, Mar 2018, Lake Tahoe, United States. pp.1-10, ⟨10.1109/WACV.2018.00194⟩

International audience; Severe background clutter is challenging in many computer vision tasks, including large-scale image retrieval. Global descriptors, that are popular due to their memory and search efficiency, are especially prone to corruption

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::78be7c95c71a125e625a005365017afb
https://hal.inria.fr/hal-02370223