Standard
On Label Granularity and Object Localization. / Cole, Elijah; Wilber, Kimberly; Van Horn, Grant; Yang, Xuan; Fornoni, Marco; Perona, Pietro; Belongie, Serge; Howard, Andrew; Aodha, Oisin Mac.
Computer Vision – ECCV 2022 : 17th European Conference, Proceedings. ed. / Shai Avidan; Gabriel Brostow; Moustapha Cissé; Giovanni Maria Farinella; Tal Hassner. Springer, 2022. p. 604-620 (Lecture Notes in Computer Science, Vol. 13670 LNCS).
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
Cole, E, Wilber, K, Van Horn, G, Yang, X, Fornoni, M, Perona, P
, Belongie, S, Howard, A & Aodha, OM 2022,
On Label Granularity and Object Localization. in S Avidan, G Brostow, M Cissé, GM Farinella & T Hassner (eds),
Computer Vision – ECCV 2022 : 17th European Conference, Proceedings. Springer, Lecture Notes in Computer Science, vol. 13670 LNCS, pp. 604-620, 17th European Conference on Computer Vision, ECCV 2022, Tel Aviv, Israel,
23/10/2022.
https://doi.org/10.1007/978-3-031-20080-9_35
APA
Cole, E., Wilber, K., Van Horn, G., Yang, X., Fornoni, M., Perona, P.
, Belongie, S., Howard, A., & Aodha, O. M. (2022).
On Label Granularity and Object Localization. In S. Avidan, G. Brostow, M. Cissé, G. M. Farinella, & T. Hassner (Eds.),
Computer Vision – ECCV 2022 : 17th European Conference, Proceedings (pp. 604-620). Springer. Lecture Notes in Computer Science Vol. 13670 LNCS
https://doi.org/10.1007/978-3-031-20080-9_35
Vancouver
Cole E, Wilber K, Van Horn G, Yang X, Fornoni M, Perona P et al.
On Label Granularity and Object Localization. In Avidan S, Brostow G, Cissé M, Farinella GM, Hassner T, editors, Computer Vision – ECCV 2022 : 17th European Conference, Proceedings. Springer. 2022. p. 604-620. (Lecture Notes in Computer Science, Vol. 13670 LNCS).
https://doi.org/10.1007/978-3-031-20080-9_35
Author
Cole, Elijah ; Wilber, Kimberly ; Van Horn, Grant ; Yang, Xuan ; Fornoni, Marco ; Perona, Pietro ; Belongie, Serge ; Howard, Andrew ; Aodha, Oisin Mac. / On Label Granularity and Object Localization. Computer Vision – ECCV 2022 : 17th European Conference, Proceedings. editor / Shai Avidan ; Gabriel Brostow ; Moustapha Cissé ; Giovanni Maria Farinella ; Tal Hassner. Springer, 2022. pp. 604-620 (Lecture Notes in Computer Science, Vol. 13670 LNCS).
Bibtex
@inproceedings{09d8230bde0e4e6f9741536132743256,
title = "On Label Granularity and Object Localization",
abstract = "Weakly supervised object localization (WSOL) aims to learn representations that encode object location using only image-level category labels. However, many objects can be labeled at different levels of granularity. Is it an animal, a bird, or a great horned owl? Which image-level labels should we use? In this paper we study the role of label granularity in WSOL. To facilitate this investigation we introduce iNatLoc500, a new large-scale fine-grained benchmark dataset for WSOL. Surprisingly, we find that choosing the right training label granularity provides a much larger performance boost than choosing the best WSOL algorithm. We also show that changing the label granularity can significantly improve data efficiency.",
author = "Elijah Cole and Kimberly Wilber and {Van Horn}, Grant and Xuan Yang and Marco Fornoni and Pietro Perona and Serge Belongie and Andrew Howard and Aodha, {Oisin Mac}",
note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 17th European Conference on Computer Vision, ECCV 2022 ; Conference date: 23-10-2022 Through 27-10-2022",
year = "2022",
doi = "10.1007/978-3-031-20080-9_35",
language = "English",
isbn = "9783031200793",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "604--620",
editor = "Shai Avidan and Gabriel Brostow and Moustapha Ciss{\'e} and Farinella, {Giovanni Maria} and Tal Hassner",
booktitle = "Computer Vision – ECCV 2022",
address = "Switzerland",
}
RIS
TY - GEN
T1 - On Label Granularity and Object Localization
AU - Cole, Elijah
AU - Wilber, Kimberly
AU - Van Horn, Grant
AU - Yang, Xuan
AU - Fornoni, Marco
AU - Perona, Pietro
AU - Belongie, Serge
AU - Howard, Andrew
AU - Aodha, Oisin Mac
N1 - Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2022
Y1 - 2022
N2 - Weakly supervised object localization (WSOL) aims to learn representations that encode object location using only image-level category labels. However, many objects can be labeled at different levels of granularity. Is it an animal, a bird, or a great horned owl? Which image-level labels should we use? In this paper we study the role of label granularity in WSOL. To facilitate this investigation we introduce iNatLoc500, a new large-scale fine-grained benchmark dataset for WSOL. Surprisingly, we find that choosing the right training label granularity provides a much larger performance boost than choosing the best WSOL algorithm. We also show that changing the label granularity can significantly improve data efficiency.
AB - Weakly supervised object localization (WSOL) aims to learn representations that encode object location using only image-level category labels. However, many objects can be labeled at different levels of granularity. Is it an animal, a bird, or a great horned owl? Which image-level labels should we use? In this paper we study the role of label granularity in WSOL. To facilitate this investigation we introduce iNatLoc500, a new large-scale fine-grained benchmark dataset for WSOL. Surprisingly, we find that choosing the right training label granularity provides a much larger performance boost than choosing the best WSOL algorithm. We also show that changing the label granularity can significantly improve data efficiency.
U2 - 10.1007/978-3-031-20080-9_35
DO - 10.1007/978-3-031-20080-9_35
M3 - Article in proceedings
AN - SCOPUS:85144546693
SN - 9783031200793
T3 - Lecture Notes in Computer Science
SP - 604
EP - 620
BT - Computer Vision – ECCV 2022
A2 - Avidan, Shai
A2 - Brostow, Gabriel
A2 - Cissé, Moustapha
A2 - Farinella, Giovanni Maria
A2 - Hassner, Tal
PB - Springer
T2 - 17th European Conference on Computer Vision, ECCV 2022
Y2 - 23 October 2022 through 27 October 2022
ER -