Papers › Localizing Objects with Self-Supervised Transformers and no Labels

Localizing Objects with Self-Supervised Transformers and no Labels

29 Sep 2021arXiv:2109.14279archive 2025-07-28

Oriane Siméoni, Gilles Puy, Huy V. Vo, Simon Roburin, Spyros Gidaris, Andrei Bursuc, Patrick Pérez, Renaud Marlet, Jean Ponce

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.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

valeoai/LOST officialmentioned in papermentioned on GitHubpytorchNOASSERTION report

lukemelas/deep-spectral-segmentation mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Object Object Discovery Single-object discovery Weakly-Supervised Object Localization

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Single-object discovery	COCO_20k	LOST + CAD	CorLoc	57.5	#6 of 10	Archive leaderboard	report
Single-object discovery	COCO_20k	LOST	CorLoc	50.7	#8 of 10	Archive leaderboard	report
Weakly-Supervised Object Localization	CUB-200-2011	LOST	Top-1 Localization Accuracy	71.3	#8 of 10	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Attention Dense Connections Layer Normalization Linear Layer Multi-Head Attention Residual Connection Softmax Vision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections