Papers › Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space...

Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization

12 Dec 2023arXiv:2312.07342archive 2025-07-28

Jiyoung Kim, Kyuhong Shim, Insu Lee, Byonghyo Shim

Unsupervised semantic segmentation (USS) aims to discover and recognize meaningful categories without any labels. For a successful USS, two key abilities are required: 1) information compression and 2) clustering capability. Previous methods have relied on feature dimension reduction for information compression, however, this approach may hinder the process of clustering. In this paper, we propose a novel USS framework called Expand-and-Quantize Unsupervised Semantic Segmentation (EQUSS), which combines the benefits of high-dimensional spaces for better clustering and product quantization for effective information compression. Our extensive experiments demonstrate that EQUSS achieves state-of-the-art results on three standard benchmarks. In addition, we analyze the entropy of USS features, which is the first step towards understanding USS from the perspective of information theory.

PaperPDF

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

ClusteringDimensionality ReductionQuantizationSegmentationSemantic SegmentationUnsupervised Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Semantic Segmentation COCO-Stuff-27 EQUSS Clustering [Accuracy] 53.8 #12 of 29 Archive leaderboard report
Unsupervised Semantic Segmentation COCO-Stuff-27 EQUSS Clustering [mIoU] 25.8 #12 of 29 Archive leaderboard report
Unsupervised Semantic Segmentation COCO-Stuff-27 EQUSS Linear Classifier [Accuracy] 75.2 #12 of 29 Archive leaderboard report
Unsupervised Semantic Segmentation COCO-Stuff-27 EQUSS Linear Classifier [mIoU] 41.2 #12 of 29 Archive leaderboard report
Unsupervised Semantic Segmentation COCO-Stuff-27 EQUSS (ViT-S) Clustering [Accuracy] 53.8 #13 of 29 Archive leaderboard report
Unsupervised Semantic Segmentation COCO-Stuff-27 EQUSS (ViT-S) Clustering [mIoU] 25.8 #13 of 29 Archive leaderboard report
Unsupervised Semantic Segmentation Cityscapes test EQUSS Accuracy 79.9 #4 of 14 Archive leaderboard report
Unsupervised Semantic Segmentation Cityscapes test EQUSS mIoU 22.0 #4 of 14 Archive leaderboard report
Unsupervised Semantic Segmentation Potsdam-3 EQUSS Accuracy 82.0 #4 of 8 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