# Unsupervised learning from video to detect foreground objects in single images

arXiv: https://arxiv.org/abs/1703.10901 · HTML: https://mlsanity.com/paper/1703.10901/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2017.

## Built on by (most cited first, 15 of 15)

- [A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends](https://mlsanity.com/paper/2301.05712/) (2023)
- [Mixed supervision for surface-defect detection: from weakly to fully supervised learning](https://mlsanity.com/paper/2104.06064/) (2021)
- [Motion-aware Contrastive Video Representation Learning via Foreground-background Merging](https://mlsanity.com/paper/2109.15130/) (2021)
- [Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video](https://mlsanity.com/paper/2310.08584/) (2023)
- [Semi-Supervised Semantic Segmentation via Gentle Teaching Assistant](https://mlsanity.com/paper/2301.07340/) (2023)
- [Hop-Count Based Self-Supervised Anomaly Detection on Attributed Networks](https://mlsanity.com/paper/2104.07917/) (2021)
- [Weakly Supervised Video Salient Object Detection](https://mlsanity.com/paper/2104.02391/) (2021)
- [A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2209.09341/) (2022)
- [Learning to Better Segment Objects from Unseen Classes with Unlabeled Videos](https://mlsanity.com/paper/2104.12276/) (2021)
- [DEVIAS: Learning Disentangled Video Representations of Action and Scene](https://mlsanity.com/paper/2312.00826/) (2023)
- [MOD-UV: Learning Mobile Object Detectors from Unlabeled Videos](https://mlsanity.com/paper/2405.14841/) (2024)
- [Video Decomposition Prior: A Methodology to Decompose Videos into Layers](https://mlsanity.com/paper/2412.04930/) (2024)
- [Self-Supervised Learning for Point Clouds Data: A Survey](https://mlsanity.com/paper/2305.11881/) (2023)
- [Source-Free Test-Time Adaptation For Online Surface-Defect Detection](https://mlsanity.com/paper/2408.09494/) (2024)
- [Ensemble Foreground Management for Unsupervised Object Discovery](https://mlsanity.com/paper/2507.20860/) (2025)

## Abstract (arXiv)

Unsupervised learning from visual data is one of the most difficult challenges in computer vision, being a fundamental task for understanding how visual recognition works. From a practical point of view, learning from unsupervised visual input has an immense practical value, as very large quantities of unlabeled videos can be collected at low cost. In this paper, we address the task of unsupervised learning to detect and segment foreground objects in single images. We achieve our goal by training a student pathway, consisting of a deep neural network. It learns to predict from a single input image (a video frame) the output for that particular frame, of a teacher pathway that performs unsupervised object discovery in video. Our approach is different from the published literature that performs unsupervised discovery in videos or in collections of images at test time. We move the unsupervised discovery phase during the training stage, while at test time we apply the standard feed-forward processing along the student pathway. This has a dual benefit: firstly, it allows in principle unlimited possibilities of learning and generalization during training, while remaining very fast at testing. Secondly, the student not only becomes able to detect in single images significantly better than its unsupervised video discovery teacher, but it also achieves state of the art results on two important current benchmarks, YouTube Objects and Object Discovery datasets. Moreover, at test time, our system is at least two orders of magnitude faster than other previous methods.