April 5, 2024, 4:45 a.m. | Alp Eren Sari, Francesco Locatello, Paolo Favar

cs.CV updates on arXiv.org arxiv.org

arXiv:2404.03392v1 Announce Type: new
Abstract: We present two practical improvement techniques for unsupervised segmentation learning. These techniques address limitations in the resolution and accuracy of predicted segmentation maps of recent state-of-the-art methods. Firstly, we leverage image post-processing techniques such as guided filtering to refine the output masks, improving accuracy while avoiding substantial computational costs. Secondly, we introduce a multi-scale consistency criterion, based on a teacher-student training scheme. This criterion matches segmentation masks predicted from regions of the input image extracted …

abstract accuracy art arxiv computational cs.cv filtering image improvement improving limitations maps masks post-processing practical processing refine resolution segmentation state tricks type unsupervised

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