paper-with-me

Papers

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

2024-12-09 · Fei Wu, Pablo Marquez-Neila, Hedyeh Rafi-Tarii, Raphael Sznitman

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.

📄 PDF Abstract BibTeX arXiv:2412.06470

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningBoundary DetectionSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Exploring UMAP in hybrid models of entropy-based and representativeness sampling for active learning in biomedical segmentation

2023-12-16 · H. S. Tan, Kuancheng Wang, Rafe McBeth

In this work, we study various hybrid models of entropy-based and representativeness sampling techniques in the context of active learning in medical segmentation, in particular examining the role of UMAP (Uniform Manifo…

Active LearningDimensionality ReductionSegmentation

Estimating Semantic Alphabet Size for LLM Uncertainty Quantification

2025-09-17 · Lucas H. McCabe, Rimon Melamed, Thomas Hartvigsen, H. Howie Huang arxiv

Many black-box techniques for quantifying the uncertainty of large language models (LLMs) rely on repeated LLM sampling, which can be computationally expensive. Therefore, practical applicability demands reliable estimat…

Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs

2025-06-03 · Jaydip Sen, Saptarshi Sengupta, Subhasis Dasgupta

This chapter explores advancements in decoding strategies for large language models (LLMs), focusing on enhancing the Locally Typical Sampling (LTS) algorithm. Traditional decoding methods, such as top-k and nucleus samp…

Abstractive Text SummarizationComputational EfficiencyDiversityStory Generation+1

Active Diffusion Subsampling

2024-06-20 · Oisin Nolan, Tristan S. W. Stevens, Wessel L. van Nierop, Ruud J. G. van Sloun

Subsampling is commonly used to mitigate costs associated with data acquisition, such as time or energy requirements, motivating the development of algorithms for estimating the fully-sampled signal of interest $x$ from …

When Imbalance Comes Twice: Active Learning under Simulated Class Imbalance and Label Shift in Binary Semantic Segmentation

2026-01-08 · Julien Combes, Alexandre Derville, Jean-François Coeurjolly arxiv

The aim of Active Learning is to select the most informative samples from an unlabelled set of data. This is useful in cases where the amount of data is large and labelling is expensive, such as in machine vision or medi…

Semantic SegmentationActive Learning