Self-supervised object detection and retrieval using unlabeled videos

Amrani E, Ben-Ari R, Shapira I, Hakim T, Bronstein AM. 2020. Self-supervised object detection and retrieval using unlabeled videos. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 9150938.

Download
No fulltext has been uploaded. References only!

Conference Paper | Published | English

Scopus indexed
Author
Amrani, Elad; Ben-Ari, Rami; Shapira, Inbar; Hakim, Tal; Bronstein, Alex M.ISTA
Abstract
Learning an object detection or retrieval system requires a large data set with manual annotations. Such data are expensive and time-consuming to create and therefore difficult to obtain on a large scale. In this work, we propose using the natural correlation in narrations and the visual presence of objects in video to learn an object detector and retriever without any manual labeling involved. We pose the problem as weakly supervised learning with noisy labels, and propose a novel object detection and retrieval 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 ten objects with manual ground truth annotation in almost 5000 frames extracted from instructional videos from the web. We demonstrate superior results compared to state-of-the-art weakly- supervised approaches and report a strongly-labeled upper bound as well. While the focus of the paper is object detection and retrieval, the proposed methodology can be applied to a broader range of noisy weakly-supervised problems.
Publishing Year
Date Published
2020-07-28
Proceedings Title
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Publisher
IEEE
Article Number
9150938
Conference
IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops
Conference Location
Seattle, WA, United States
Conference Date
2020-06-14 – 2020-06-19
eISSN
IST-REx-ID

Cite this

Amrani E, Ben-Ari R, Shapira I, Hakim T, Bronstein AM. Self-supervised object detection and retrieval using unlabeled videos. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE; 2020. doi:10.1109/cvprw50498.2020.00485
Amrani, E., Ben-Ari, R., Shapira, I., Hakim, T., & Bronstein, A. M. (2020). Self-supervised object detection and retrieval using unlabeled videos. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Seattle, WA, United States: IEEE. https://doi.org/10.1109/cvprw50498.2020.00485
Amrani, Elad, Rami Ben-Ari, Inbar Shapira, Tal Hakim, and Alex M. Bronstein. “Self-Supervised Object Detection and Retrieval Using Unlabeled Videos.” In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, 2020. https://doi.org/10.1109/cvprw50498.2020.00485.
E. Amrani, R. Ben-Ari, I. Shapira, T. Hakim, and A. M. Bronstein, “Self-supervised object detection and retrieval using unlabeled videos,” in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, United States, 2020.
Amrani E, Ben-Ari R, Shapira I, Hakim T, Bronstein AM. 2020. Self-supervised object detection and retrieval using unlabeled videos. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 9150938.
Amrani, Elad, et al. “Self-Supervised Object Detection and Retrieval Using Unlabeled Videos.” 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 9150938, IEEE, 2020, doi:10.1109/cvprw50498.2020.00485.

Export

Marked Publications

Open Data ISTA Research Explorer

Search this title in

Google Scholar
ISBN Search