Papers › Unsupervised Multi-object Segmentation Using Attention and Soft-argmax

Unsupervised Multi-object Segmentation Using Attention and Soft-argmax

26 May 2022arXiv:2205.13271archive 2025-07-28

Bruno Sauvalle, Arnaud de La Fortelle

We introduce a new architecture for unsupervised object-centric representation learning and multi-object detection and segmentation, which uses a translation-equivariant attention mechanism to predict the coordinates of the objects present in the scene and to associate a feature vector to each object. A transformer encoder handles occlusions and redundant detections, and a convolutional autoencoder is in charge of background reconstruction. We show that this architecture significantly outperforms the state of the art on complex synthetic benchmarks.

PaperPDFCode

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

Code

BrunoSauvalle/AST officialpytorch 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

ObjectObject DetectionRepresentation LearningSemantic SegmentationTranslationUnsupervised Object Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Object Segmentation ClevrTex AST-Seg-B3-CT MSE 139±7 #1 of 12 Archive leaderboard report
Unsupervised Object Segmentation ClevrTex AST-Seg-B3-CT mIoU 79.58±0.54 #1 of 12 Archive leaderboard report
Unsupervised Object Segmentation ClevrTex AST MSE 167± 1 #2 of 12 Archive leaderboard report
Unsupervised Object Segmentation ClevrTex AST mIoU 66.62± 0.80 #2 of 12 Archive leaderboard report
Unsupervised Object Segmentation ObjectsRoom AST ARI-FG 0.87 #1 of 5 Archive leaderboard report
Unsupervised Object Segmentation ShapeStacks AST ARI-FG 0.82 #1 of 5 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.

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