Localizing Objects with Self-Supervised Transformers and no Labels

Code

• github.com/valeoai/LOST
  OfficialIn paperpytorch★ 263
• github.com/lukemelas/deep-spectral-segmentation
  pytorch★ 236

Abstract

Localizing objects in image collections without supervision can help to avoid expensive annotation campaigns. We propose a simple approach to this problem, that leverages the activation features of a vision transformer pre-trained in a self-supervised manner. Our method, LOST, does not require any external object proposal nor any exploration of the image collection; it operates on a single image. Yet, we outperform state-of-the-art object discovery methods by up to 8 CorLoc points on PASCAL VOC 2012. We also show that training a class-agnostic detector on the discovered objects boosts results by another 7 points. Moreover, we show promising results on the unsupervised object discovery task. The code to reproduce our results can be found at https://github.com/valeoai/LOST.

Tasks

Benchmark Results

Reproductions