Superpixel Segmentation

Follow this topic Ask about this topic

Latest papers

9 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

LACToS: Local Anomaly Detection via Conditional Typicality of Superpixels
Oct 22, 2026Jihoon Hong, Alireza Kheirandish, Rohan Sanda +1Superpixel Segmentation Anomaly Detection
Georgia Institute of Technology, Atlanta, GA, USA · Stanford University, Stanford, CA, USA · Cohere
Bayesian-Optimized Superpixel-GrabCut for Traceable Optic Disc Segmentation
Aug 29, 2026Shraddha Changune, Vivek Noel Soren, Gautam Das +1Superpixel Segmentation Optic Disc Segmentation
Electrical Engineering Indian Institute of Technology Delhi, India · Electronics and Communication Engineering Gauhati University Guwahati, India
Superpixel-Based QUBO for Scalable Quantum-Enhanced Medical Image Segmentation
Jul 27, 2026Mohammad Chalhoub, Mahdi Chehimi, Laia Domingo +3Image Segmentation Superpixel Segmentation
Department of Electrical and Computer Engineering, American University of Beirut, Beirut, Lebanon · Centre de Visi´o per Computador (CVC), Barcelona, Spain · Ingenii Inc., New York, USA +3
Deep Spatially-Regularized and Superpixel-Based Diffusion Learning for Unsupervised Hyperspectral Image Clustering
Apr 14, 2026Vutichart Buranasiri, James M. MurphySuperpixel Segmentation Clustering
Department of Mathematics, Tufts University, Medford, MA 02155, USA
H-SPAM: Hierarchical Superpixel Anything Model
Apr 13, 2026Julien Walther, Rémi Giraud, Michaël ClémentSuperpixel Segmentation Image Segmentation
Univ. Bordeaux, CNRS, Bordeaux INP, IMS, UMR 5218, France · Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800, France
Square Superpixel Generation and Representation Learning via Granular Ball Computing
Mar 31, 2026Shuyin Xia, Meng Yang, Dawei Dai +6Superpixel Segmentation Visual Representation Learning
Shuyin Xia, Meng Yang, Dawei Dai, Fan Chen, Shilin Zhao and Junwei Han are with Chongqing University of Posts and Telecommunications, Chongqing, China. · Xinbo Gao and Wen Lu are with Xidian University, Xi’an, China. · Guoyin Wang is with Chongqing Normal University, Chongqing, China.
Computer Vision with a Superpixelation Camera
Mar 27, 2026Sasidharan Mahalingam, Rachel Brown, Atul IngleSuperpixel Segmentation Image Segmentation
Portland State University · Willamette University
Segmenting Low-Contrast XCTs of Concrete: An Unsupervised Approach
Feb 23, 2026Kaustav Das, Gaston Rauchs, Jan Sykora +1Image Segmentation Superpixel Segmentation
Department of Mechanics, Faculty of Civil Engineering, Czech Technical University in Prague, Thákurova 7, 166 29 Prague 6, Czech Republic · Structural Composites Unit, Luxembourg Institute of Science and Technology (LIST), 5 avenue des Hauts-Fourneaux L-4362 Esch-sur-Alzette, Luxembourg
Superpixel-Based Image Segmentation Using Squared 2-Wasserstein Distances
Jan 22, 2026Jisui Huang, Andreas Alpers, Ke Chen +1Superpixel Segmentation Image Segmentation
Department of Mathematical Sciences, Centre for Mathematical Imaging Techniques (CMIT), University of Liverpool, Peach Street, Liverpool, L697ZL, Merseyside, United Kingdom. · School of Mathematical Sciences, Capital Normal University, West Third Ring Road North, Haidian District, Beijing, 100084, China. · Department of Mathematics and Statistics, University of Strathclyde, Richmond St, Glasgow, G11XH, Scotland, United Kingdom. +1

Oct 22, 2026J/K move · Enter open · S save

LACToS: Local Anomaly Detection via Conditional Typicality of Superpixels

Jihoon Hong, Alireza Kheirandish, Rohan Sanda, Sara Fridovich-Keil

Georgia Institute of Technology, Atlanta, GA, USA · Stanford University, Stanford, CA, USA · Cohere

Superpixel Segmentation Anomaly Detection Anomaly Localization OOD Detection

Open paper AskPDF arXiv

Local anomaly detection is the task of identifying spatially confined anomalous or out-of-distribution (OOD) regions within an otherwise in-distribution (ID) image. Most existing methods are designed for a specific context, with a strong focus on industrial defect detection, where they achieve excellent performance on well-established benchmarks. However, we observe that these methods can exhibit significant performance drops in other contexts, especially when the inlier distribution is multimodal. To account for this inlier complexity, we propose LACToS, a principled local OOD detection method based on statistical typicality and made tractable through two innovations: (i) grouping pixels into superpixels and (ii) using a computationally efficient proxy to estimate typicality. We evaluate LACToS across three diverse applications spanning medical imaging, human faces, and X-ray security screening. LACToS performs more robustly than prior methods across these benchmarks. The code is released here: https://github.com/voilalab/LACToS.