# Object-Centric Representation Learning from Unlabeled Videos

arXiv: https://arxiv.org/abs/1612.00500 · HTML: https://mlsanity.com/paper/1612.00500/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2016.

## Built on by (most cited first, 3 of 3)

- [Slot-VPS: Object-centric Representation Learning for Video Panoptic Segmentation](https://mlsanity.com/paper/2112.08949/) (2021)
- [Understanding Video Transformers via Universal Concept Discovery](https://mlsanity.com/paper/2401.10831/) (2024)
- [Collecting Consistently High Quality Object Tracks with Minimal Human Involvement by Using Self-Supervised Learning to Detect Tracker Errors](https://mlsanity.com/paper/2405.03643/) (2024)

## Abstract (arXiv)

Supervised (pre-)training currently yields state-of-the-art performance for representation learning for visual recognition, yet it comes at the cost of (1) intensive manual annotations and (2) an inherent restriction in the scope of data relevant for learning. In this work, we explore unsupervised feature learning from unlabeled video. We introduce a novel object-centric approach to temporal coherence that encourages similar representations to be learned for object-like regions segmented from nearby frames. Our framework relies on a Siamese-triplet network to train a deep convolutional neural network (CNN) representation. Compared to existing temporal coherence methods, our idea has the advantage of lightweight preprocessing of the unlabeled video (no tracking required) while still being able to extract object-level regions from which to learn invariances. Furthermore, as we show in results on several standard datasets, our method typically achieves substantial accuracy gains over competing unsupervised methods for image classification and retrieval tasks.