Self-Supervised Human Detection and Segmentation via Background Inpainting
Katircioglu I, Rhodin H, Constantin V, Sporri J, Salzmann M, Fua P (2022)
IEEE Transactions on Pattern Analysis and Machine Intelligence 44(12): 9574-9588.
Zeitschriftenaufsatz
| Veröffentlicht | Englisch
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Katircioglu, Isinsu;
Rhodin, HelgeUniBi ;
Constantin, Victor;
Sporri, Jorg;
Salzmann, Mathieu;
Fua, Pascal
Abstract / Bemerkung
While supervised object detection and segmentation methods achieve impressive accuracy, they generalize poorly to images whose appearance significantly differs from the data they have been trained on. To address this when annotating data is prohibitively expensive, we introduce a self-supervised detection and segmentation approach that can work with single images captured by a potentially moving camera. At the heart of our approach lies the observation that object segmentation and background reconstruction are linked tasks, and that, for structured scenes, background regions can be re-synthesized from their surroundings, whereas regions depicting the moving object cannot. We encode this intuition into a self-supervised loss function that we exploit to train a proposal-based segmentation network. To account for the discrete nature of the proposals, we develop a Monte Carlo-based training strategy that allows the algorithm to explore the large space of object proposals. We apply our method to human detection and segmentation in images that visually depart from those of standard benchmarks and outperform existing self-supervised methods.
Stichworte
IEEE Transactions on Pattern Analysis and Machine Intelligence
Erscheinungsjahr
2022
Zeitschriftentitel
IEEE Transactions on Pattern Analysis and Machine Intelligence
Band
44
Ausgabe
12
Seite(n)
9574-9588
ISSN
0162-8828
eISSN
2160-9292, 1939-3539
Page URI
https://pub.uni-bielefeld.de/record/2991919
Zitieren
Katircioglu I, Rhodin H, Constantin V, Sporri J, Salzmann M, Fua P. Self-Supervised Human Detection and Segmentation via Background Inpainting. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2022;44(12):9574-9588.
Katircioglu, I., Rhodin, H., Constantin, V., Sporri, J., Salzmann, M., & Fua, P. (2022). Self-Supervised Human Detection and Segmentation via Background Inpainting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(12), 9574-9588. https://doi.org/10.1109/TPAMI.2021.3123902
Katircioglu, Isinsu, Rhodin, Helge, Constantin, Victor, Sporri, Jorg, Salzmann, Mathieu, and Fua, Pascal. 2022. “Self-Supervised Human Detection and Segmentation via Background Inpainting”. IEEE Transactions on Pattern Analysis and Machine Intelligence 44 (12): 9574-9588.
Katircioglu, I., Rhodin, H., Constantin, V., Sporri, J., Salzmann, M., and Fua, P. (2022). Self-Supervised Human Detection and Segmentation via Background Inpainting. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 9574-9588.
Katircioglu, I., et al., 2022. Self-Supervised Human Detection and Segmentation via Background Inpainting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(12), p 9574-9588.
I. Katircioglu, et al., “Self-Supervised Human Detection and Segmentation via Background Inpainting”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, 2022, pp. 9574-9588.
Katircioglu, I., Rhodin, H., Constantin, V., Sporri, J., Salzmann, M., Fua, P.: Self-Supervised Human Detection and Segmentation via Background Inpainting. IEEE Transactions on Pattern Analysis and Machine Intelligence. 44, 9574-9588 (2022).
Katircioglu, Isinsu, Rhodin, Helge, Constantin, Victor, Sporri, Jorg, Salzmann, Mathieu, and Fua, Pascal. “Self-Supervised Human Detection and Segmentation via Background Inpainting”. IEEE Transactions on Pattern Analysis and Machine Intelligence 44.12 (2022): 9574-9588.
Link(s) zu Volltext(en)
Access Level
Closed Access