Active Learning with Context Sampling and One-vs-Rest Entropy for Semantic Segmentation

Autor:	Wu, Fei, Marquez-Neila, Pablo, Rafi-Tarii, Hedyeh, Sznitman, Raphael
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Multi-class semantic segmentation remains a cornerstone challenge in computer vision. Yet, dataset creation remains excessively demanding in time and effort, especially for specialized domains. Active Learning (AL) mitigates this challenge by selecting data points for annotation strategically. However, existing patch-based AL methods often overlook boundary pixels critical information, essential for accurate segmentation. We present OREAL, a novel patch-based AL method designed for multi-class semantic segmentation. OREAL enhances boundary detection by employing maximum aggregation of pixel-wise uncertainty scores. Additionally, we introduce one-vs-rest entropy, a novel uncertainty score function that computes class-wise uncertainties while achieving implicit class balancing during dataset creation. Comprehensive experiments across diverse datasets and model architectures validate our hypothesis. Comment: WACV 2025, 8 pages
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2412.06470 Zobrazit plný text záznamu View this record from Arxiv