Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection

no code implementations • 21 Dec 2023 • Soopil Kim, Sion An, Philip Chikontwe, Myeongkyun Kang, Ehsan Adeli, Kilian M. Pohl, Sang Hyun Park

In this study, we introduce a novel component segmentation model for LA detection that leverages a few labeled samples and unlabeled images sharing logical constraints.

Anomaly Detection Segmentation +1

Content Preserving Image Translation with Texture Co-occurrence and Spatial Self-Similarity for Texture Debiasing and Domain Adaptation

no code implementations • 15 Oct 2021 • Myeongkyun Kang, Dongkyu Won, Miguel Luna, Philip Chikontwe, Kyung Soo Hong, June Hong Ahn, Sang Hyun Park

Models trained on datasets with texture bias usually perform poorly on out-of-distribution samples since biased representations are embedded into the model.

Domain Adaptation Translation

Mixing-AdaSIN: Constructing a De-biased Dataset using Adaptive Structural Instance Normalization and Texture Mixing

no code implementations • 26 Mar 2021 • Myeongkyun Kang, Philip Chikontwe, Miguel Luna, Kyung Soo Hong, June Hong Ahn, Sang Hyun Park

Our experiments show that classifiers trained with de-biased generated images report improved in-distribution performance and generalization on an external COVID-19 dataset.

Computed Tomography (CT)