</> Code with Papers by Syntology

Papers › Causal Unsupervised Semantic Segmentation

Causal Unsupervised Semantic Segmentation

11 Oct 2023arXiv:2310.07379archive 2025-07-28

Junho Kim, Byung-Kwan Lee, Yong Man Ro

Unsupervised semantic segmentation aims to achieve high-quality semantic grouping without human-labeled annotations. With the advent of self-supervised pre-training, various frameworks utilize the pre-trained features to train prediction heads for unsupervised dense prediction. However, a significant challenge in this unsupervised setup is determining the appropriate level of clustering required for segmenting concepts. To address it, we propose a novel framework, CAusal Unsupervised Semantic sEgmentation (CAUSE), which leverages insights from causal inference. Specifically, we bridge intervention-oriented approach (i.e., frontdoor adjustment) to define suitable two-step tasks for unsupervised prediction. The first step involves constructing a concept clusterbook as a mediator, which represents possible concept prototypes at different levels of granularity in a discretized form. Then, the mediator establishes an explicit link to the subsequent concept-wise self-supervised learning for pixel-level grouping. Through extensive experiments and analyses on various datasets, we corroborate the effectiveness of CAUSE and achieve state-of-the-art performance in unsupervised semantic segmentation.

PaperPDFCode

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

Code

ByungKwanLee/Causal-Unsupervised-Segmentation officialmentioned 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

Causal InferencePredictionSegmentationSelf-Supervised LearningSemantic SegmentationUnsupervised Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Semantic Segmentation COCO-Stuff-171 CAUSE-TR (ViT-S/8) Pixel Accuracy 46.6 #1 of 4 Archive leaderboard report
Unsupervised Semantic Segmentation COCO-Stuff-171 CAUSE-TR (ViT-S/8) mIoU 15.2 #1 of 4 Archive leaderboard report
Unsupervised Semantic Segmentation COCO-Stuff-27 CAUSE (DINOv2, ViT-B/14) Clustering [Accuracy] 78.0 #3 of 29 Archive leaderboard report
Unsupervised Semantic Segmentation COCO-Stuff-27 CAUSE (DINOv2, ViT-B/14) Clustering [mIoU] 45.3 #3 of 29 Archive leaderboard report
Unsupervised Semantic Segmentation COCO-Stuff-27 CAUSE (ViT-B/8) Clustering [Accuracy] 74.9 #4 of 29 Archive leaderboard report
Unsupervised Semantic Segmentation COCO-Stuff-27 CAUSE (ViT-B/8) Clustering [mIoU] 41.9 #4 of 29 Archive leaderboard report
Unsupervised Semantic Segmentation COCO-Stuff-81 CAUSE-TR (ViT-S/8) Pixel Accuracy 75.2 #1 of 4 Archive leaderboard report
Unsupervised Semantic Segmentation COCO-Stuff-81 CAUSE-TR (ViT-S/8) mIoU 21.2 #1 of 4 Archive leaderboard report
Unsupervised Semantic Segmentation COCO-Stuff-81 CAUSE-MLP (ViT-S/8) Pixel Accuracy 78.8 #2 of 4 Archive leaderboard report
Unsupervised Semantic Segmentation COCO-Stuff-81 CAUSE-MLP (ViT-S/8) mIoU 19.1 #2 of 4 Archive leaderboard report
Unsupervised Semantic Segmentation PASCAL VOC 2012 val CAUSE (iBOT, ViT-B/16) Clustering [mIoU] 53.4 #1 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation PASCAL VOC 2012 val CAUSE (ViT-B/8) Clustering [mIoU] 53.3 #2 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation PASCAL VOC 2012 val CAUSE (DINOv2, ViT-B/14) Clustering [mIoU] 53.2 #3 of 12 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