Learning to detect and retrieve objects from unlabeled videos
Amrani E, Ben-Ari R, Hakim T, Bronstein AM. 2020. Learning to detect and retrieve objects from unlabeled videos. 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). 17th IEEE/CVF International Conference on Computer Vision Workshop, 9022341.
Download (ext.)
Conference Paper
| Published
| English
Scopus indexed
Author
Amrani, Elad;
Ben-Ari, Rami;
Hakim, Tal;
Bronstein, Alex M.ISTA 

Abstract
Learning an object detection or retrieval system requires a large data set with manual annotations. Such data sets are expensive and time consuming to create and therefore difficult to obtain on a large scale. In this work, we propose to exploit the natural correlation in narrations and the visual presence of objects in video, to learn an object detector and retrieval without any manual labeling involved. We pose the problem as weakly supervised learning with noisy labels, and propose a novel object detection paradigm under these constraints. We handle the background rejection by using contrastive samples and confront the high level of label noise with a new clustering score. Our evaluation is based on a set of 11 manually annotated objects in over 5000 frames. We show comparison to a weakly-supervised approach as baseline and provide a strongly labeled upper bound.
Publishing Year
Date Published
2020-03-05
Proceedings Title
2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
Publisher
IEEE
Article Number
9022341
Conference
17th IEEE/CVF International Conference on Computer Vision Workshop
Conference Location
Seoul, Korea (South)
Conference Date
2019-10-27 – 2019-10-28
ISBN
eISSN
IST-REx-ID
Cite this
Amrani E, Ben-Ari R, Hakim T, Bronstein AM. Learning to detect and retrieve objects from unlabeled videos. In: 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). IEEE; 2020. doi:10.1109/iccvw.2019.00567
Amrani, E., Ben-Ari, R., Hakim, T., & Bronstein, A. M. (2020). Learning to detect and retrieve objects from unlabeled videos. In 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). Seoul, Korea (South): IEEE. https://doi.org/10.1109/iccvw.2019.00567
Amrani, Elad, Rami Ben-Ari, Tal Hakim, and Alex M. Bronstein. “Learning to Detect and Retrieve Objects from Unlabeled Videos.” In 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). IEEE, 2020. https://doi.org/10.1109/iccvw.2019.00567.
E. Amrani, R. Ben-Ari, T. Hakim, and A. M. Bronstein, “Learning to detect and retrieve objects from unlabeled videos,” in 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), Seoul, Korea (South), 2020.
Amrani E, Ben-Ari R, Hakim T, Bronstein AM. 2020. Learning to detect and retrieve objects from unlabeled videos. 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). 17th IEEE/CVF International Conference on Computer Vision Workshop, 9022341.
Amrani, Elad, et al. “Learning to Detect and Retrieve Objects from Unlabeled Videos.” 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), 9022341, IEEE, 2020, doi:10.1109/iccvw.2019.00567.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Link(s) to Main File(s)
Access Level

Export
Marked PublicationsOpen Data ISTA Research Explorer
Sources
arXiv 1905.11137