paper-with-me

Papers

CLASP: Adaptive Spectral Clustering for Unsupervised Per-Image Segmentation

2025-09-29 · Max Curie, Paulo da Costa 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

📄 PDF Abstract BibTeX arXiv:2509.25016

Code (0)

등록된 구현이 없습니다.

Tasks

Image Segmentation

Similar Papers 제목 키워드 기반

Unsupervised Spatial-spectral Hyperspectral Image Reconstruction and Clustering with Diffusion Geometry

2022-04-28 · Kangning Cui, Ruoning Li, Sam L. Polk, James M. Murphy 외

Hyperspectral images, which store a hundred or more spectral bands of reflectance, have become an important data source in natural and social sciences. Hyperspectral images are often generated in large quantities at a re…

ClusteringImage Reconstruction

CLIP-Guided Adaptable Self-Supervised Learning for Human-Centric Visual Tasks

2026-01-19 · Mingshuang Luo, Ruibing Hou, Bo Chao, Hong Chang 외 arxiv

Human-centric visual analysis plays a pivotal role in diverse applications, including surveillance, healthcare, and human-computer interaction. With the emergence of large-scale unlabeled human image datasets, there is a…

Unsupervised Pre-trainingSelf-Supervised LearningRepresentation Learning

CLASP: Class-Adaptive Layer Fusion and Dual-Stage Pruning for Multimodal Large Language Models

2026-04-14 · Yunkai Dang, Yizhu Jiang, Yifan Jiang, Qi Fan 외 arxiv

Multimodal Large Language Models (MLLMs) suffer from substantial computational overhead due to the high redundancy in visual token sequences. Existing approaches typically address this issue using single-layer Vision Tra…

Adaptive Affinity Matrix for Unsupervised Metric Learning

2015-11-13 · Yaoyi Li, Junxuan Chen, Hongtao Lu

Spectral clustering is one of the most popular clustering approaches with the capability to handle some challenging clustering problems. Most spectral clustering methods provide a nonlinear map from the data manifold to …

ClusteringMetric Learning

Unbalanced Optimal Transport Dictionary Learning for Unsupervised Hyperspectral Image Clustering

2026-03-10 · Joshua Lentz, Nicholas Karris, Alex Cloninger, James M. Murphy arxiv

Hyperspectral images capture vast amounts of high-dimensional spectral information about a scene, making labeling an intensive task that is resistant to out-of-the-box statistical methods. Unsupervised learning of cluste…

Image Clustering