Papers › Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentation

Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentation

24 Nov 2023arXiv:2311.14665archive 2025-07-28

Paul Engstler, Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina

Self-supervised learning (SSL) can be used to solve complex visual tasks without human labels. Self-supervised representations encode useful semantic information about images, and as a result, they have already been used for tasks such as unsupervised semantic segmentation. In this paper, we investigate self-supervised representations for instance segmentation without any manual annotations. We find that the features of different SSL methods vary in their level of instance-awareness. In particular, DINO features, which are known to be excellent semantic descriptors, lack behind MAE features in their sensitivity for separating instances.

PaperPDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Instance SegmentationSegmentationSelf-Supervised LearningSemantic SegmentationSensitivityUnsupervised Instance SegmentationUnsupervised Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Instance Segmentation COCO val2017 Self-Training (MAE) AP 5.2 #3 of 5 Archive leaderboard report
Unsupervised Instance Segmentation COCO val2017 Self-Training (MAE) AP50 12.1 #3 of 5 Archive leaderboard report
Unsupervised Instance Segmentation COCO val2017 Self-Training (MAE) AP75 3.7 #3 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.

Methods

AttentionDINODense ConnectionsLayer NormalizationLinear LayerMAEMulti-Head AttentionResidual ConnectionSoftmaxVision 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