Edge-guided and Class-balanced Active Learning for Semantic Segmentation of Aerial Images

2024-05-28 · Lianlei Shan, Weiqiang Wang, Ke Lv, Bin Luo

Semantic segmentation requires pixel-level annotation, which is time-consuming. Active Learning (AL) is a promising method for reducing data annotation costs. Due to the gap between aerial and natural images, the previous AL methods are not ideal, mainly caused by unreasonable labeling units and the neglect of class imbalance. Previous labeling units are based on images or regions, which does not consider the characteristics of segmentation tasks and aerial images, i.e., the segmentation network often makes mistakes in the edge region, and the edge of aerial images is often interlaced and irregular. Therefore, an edge-guided labeling unit is proposed and supplemented as the new unit. On the other hand, the class imbalance is severe, manifested in two aspects: the aerial image is seriously imbalanced, and the AL strategy does not fully consider the class balance. Both seriously affect the performance of AL in aerial images. We comprehensively ensure class balance from all steps that may occur imbalance, including initial labeled data, subsequent labeled data, and pseudo-labels. Through the two improvements, our method achieves more than 11.2\% gains compared to state-of-the-art methods on three benchmark datasets, Deepglobe, Potsdam, and Vaihingen, and more than 18.6\% gains compared to the baseline. Sufficient ablation studies show that every module is indispensable. Furthermore, we establish a fair and strong benchmark for future research on AL for aerial image segmentation.

📄 PDF Abstract BibTeX arXiv:2405.18078

Code (0)

등록된 구현이 없습니다.

Tasks

Active Learning Image Segmentation Segmentation Semantic Segmentation

BaSAL: Size-Balanced Warm Start Active Learning for LiDAR Semantic Segmentation

2023-10-12 · Jiarong Wei, Yancong Lin, Holger Caesar

Active learning strives to reduce the need for costly data annotation, by repeatedly querying an annotator to label the most informative samples from a pool of unlabeled data, and then training a model from these samples…

Active Learning LIDAR Semantic Segmentation Semantic Segmentation

Class Balanced Dynamic Acquisition for Domain Adaptive Semantic Segmentation using Active Learning

2023-11-23 · Marc Schachtsiek, Simone Rossi, Thomas Hannagan

Domain adaptive active learning is leading the charge in label-efficient training of neural networks. For semantic segmentation, state-of-the-art models jointly use two criteria of uncertainty and diversity to select tra…

Active Learning Diversity Semantic Segmentation

Medical Knowledge-Guided Deep Learning for Imbalanced Medical Image Classification

2021-11-20 · Long Gao, Chang Liu, Dooman Arefan, Ashok Panigrahy 외

Deep learning models have gained remarkable performance on a variety of image classification tasks. However, many models suffer from limited performance in clinical or medical settings when data are imbalanced. To addres…

Classification Deep Learning image-classification Image Classification+2

A Semantics-Guided Class Imbalance Learning Model for Zero-Shot Classification

2019-08-26 · Zhong Ji, Xuejie Yu, Yunlong Yu, Yanwei Pang 외

Zero-Shot Classification (ZSC) equips the learned model with the ability to recognize the visual instances from the novel classes via constructing the interactions between the visual and the semantic modalities. In contr…

General Classification image-classification Image Classification Transfer Learning+2

Resolving Long-Tail Ambiguity in Unsupervised 3D Point Cloud Segmentation with Language Priors

2026-05-20 · Siqi Wei, Hongbin Xu, Feng Xiao, Tian Lan 외 arxiv

Existing approaches for unsupervised 3D point cloud segmentation predominantly rely on a purely visual similarity-based learning-by-clustering paradigm, which suffers from a fundamental limitation: long-tail ambiguity. I…

Point Cloud Segmentation Point Clouds