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

Source: [Active Learning with Context Sampling and One-vs-Rest Entropy for Semantic Segmentation](<https://www.sota2.com/research/paper/68fa777c1e209131cea73829>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:14.696Z

Authors: Fei Wu, Pablo Marquez-Neila, Hedyeh Rafi-Tarii, Raphael Sznitman

Published: 2024-12-09T13:15:52.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2412.06470>)

[PDF](<https://arxiv.org/pdf/2412.06470.pdf>)