CLASP: Adaptive Spectral Clustering for Unsupervised Per-Image Segmentation
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
Code (0)
등록된 구현이 없습니다.
Tasks
Image SegmentationSimilar Papers 제목 키워드 기반
Unsupervised Spatial-spectral Hyperspectral Image Reconstruction and Clustering with Diffusion Geometry
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 ReconstructionCLIP-Guided Adaptable Self-Supervised Learning for Human-Centric Visual Tasks
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 LearningCLASP: Class-Adaptive Layer Fusion and Dual-Stage Pruning for Multimodal Large Language Models
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
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 LearningUnbalanced Optimal Transport Dictionary Learning for Unsupervised Hyperspectral Image Clustering
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