mlsanityData to 14 Oct 2026

CLASP: Adaptive Spectral Clustering for Unsupervised Per-Image Segmentation

arXiv 2509.25016 ↗First posted 29 Sep 2025cs.CV cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce CLASP (Clustering via Adaptive Spectral Processing), a lightweight framework for unsupervised image segmentation that operates without any labeled data or finetuning. CLASP first extracts per patch features using a self supervised ViT encoder (DINO); then, it builds an affinity matrix and applies spectral clustering. To avoid manual tuning, we select the segment count automatically with a eigengap silhouette search, and we sharpen the boundaries with a fully connected DenseCRF. Despite its simplicity and training free nature, CLASP attains competitive mIoU and pixel accuracy on COCO Stuff and ADE20K, matching recent unsupervised baselines. The zero training design makes CLASP a strong, easily reproducible baseline for large unannotated corpora especially common in digital advertising and marketing workflows such as brand safety screening, creative asset curation, and social media content moderation

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 30 references that are in the map. First posted on arXiv 29 Sep 2025.

Builds on

23 of 30 references.

References · 23

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  6. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  7. 2016Pyramid Scene Parsing Networkcited by 2,479
  8. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  9. 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 903
  10. 2023Vision Transformers Need Registerscited by 871
  11. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 864
  12. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 455
11 more
  1. 2022Unsupervised Semantic Segmentation by Distilling Feature Correspondencescited by 241
  2. 2023Cut and Learn for Unsupervised Object Detection and Instance Segmentationcited by 187
  3. 2022Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cutcited by 167
  4. 2021PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clusteringcited by 163
  5. 2022Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localizationcited by 150
  6. 2023Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusioncited by 131
  7. 2022ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentationcited by 42
  8. 2023Unsupervised Universal Image Segmentationcited by 35
  9. 2024Segment Anything without Supervisioncited by 28
  10. 2024EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentationcited by 27
  11. 2023Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Samplingcited by 19

Built on by

Not cited yet.