0

Unsupervised Representation Learning by Sorting Sequences

An unsupervised learning approach using video frames for representation learning through a sequence sorting task, demonstrating effective pre-training on high-level recognition tasks.

Year
2017
Venue
unsupervised-representation-learning-by-3
Authors
4
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/1708.01246ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

We present an unsupervised representation learning approach using videos without semantic labels. We leverage the temporal coherence as a supervisory signal by formulating representation learning as a sequence sorting task. We take temporally shuffled frames (i.e., in non-chronological order) as inputs and train a convolutional neural network to sort the shuffled sequences. Similar to comparison-based sorting algorithms, we propose to extract features from all frame pairs and aggregate them to predict the correct order. As sorting shuffled image sequence requires an understanding of the statistical temporal structure of images, training with such a proxy task allows us to learn rich and generalizable visual representation. We validate the effectiveness of the learned representation using our method as pre-training on high-level recognition problems. The experimental results show that our method compares favorably against state-of-the-art methods on action recognition, image classification and object detection tasks.

Authors

4