# Object-Centric Representation Learning from Unlabeled Videos

Source: [Object-Centric Representation Learning from Unlabeled Videos](<https://www.sota2.com/research/paper/68fa62fe1e209131ce9fc0c6>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:32.890Z

Authors: Ruohan Gao, Dinesh Jayaraman, Kristen Grauman

Published: 2016-12-01T22:36:20.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1612.00500>)

[PDF](<https://arxiv.org/pdf/1612.00500.pdf>)
