all AI news
Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learning
March 12, 2024, 4:47 a.m. | Woo-Jin Ahn, Geun-Yeong Yang, Hyun-Duck Choi, Myo-Taeg Lim
cs.CV updates on arXiv.org arxiv.org
Abstract: Deep learning models for semantic segmentation often experience performance degradation when deployed to unseen target domains unidentified during the training phase. This is mainly due to variations in image texture (\ie style) from different data sources. To tackle this challenge, existing domain generalized semantic segmentation (DGSS) methods attempt to remove style variations from the feature. However, these approaches struggle with the entanglement of style and content, which may lead to the unintentional removal of crucial …
abstract alignment arxiv blind challenge covariance cs.cv data data sources deep learning domain domains experience generalized image performance segmentation semantic style texture training type unidentified via
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US