6 citations · 8 across the 4 of their papers we have counts for
4 papers · 1 filter
Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection
Soopil Kim, Sion An, Philip Chikontwe +4
Logical anomalies (LA) refer to data violating underlying logical constraints e.g., the quantity, arrangement, or composition of components within an image. Detecting accurately su…
Feature Re-calibration based Multiple Instance Learning for Whole Slide Image Classification
Philip Chikontwe, Soo Jeong Nam, Heounjeong Go +3
Whole slide image (WSI) classification is a fundamental task for the diagnosis and treatment of diseases; but, curation of accurate labels is time-consuming and limits the applicat…
Uncertainty-Aware Semi-Supervised Few Shot Segmentation
Soopil Kim, Philip Chikontwe, Sang Hyun Park
Few shot segmentation (FSS) aims to learn pixel-level classification of a target object in a query image using only a few annotated support samples. This is challenging as it requi…
Content Preserving Image Translation with Texture Co-occurrence and Spatial Self-Similarity for Texture Debiasing and Domain Adaptation
Myeongkyun Kang, Dongkyu Won, Miguel Luna +4
Models trained on datasets with texture bias usually perform poorly on out-of-distribution samples since biased representations are embedded into the model. Recently, various image…