Confidence-Guided Joint Complementary Learning for Weakly Annotated Remote Sensing Object Segmentation
- 10 February 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-16
Abstract
Object segmentation from weakly annotated remote sensing images (RSIs) is an essential task that helps substantially reduce pixelwise labeling costs. Although mainstream multistage methods have achieved great performance, they generally suffer from high implementation complexity, which limits their practical application. On the other hand, for a single-stage scheme that can be trained in one cycle, error accumulation during joint optimization results in performance degradation. To address these issues, we propose a confidence-guided joint complementary learning (CGJCL) framework for remote sensing object segmentation under image-level annotations that can be easily trained in a single stage and achieves satisfactory performance. CGJCL integrates the localization and segmentation network into a unified framework that employs a joint complementary learning strategy, collaboratively enhancing the performance of each subnetwork. First, a confidence-guided pseudolabel refinement (CGPLR) module is developed to fuse the complementary semantic information of the localization clues and the object boundary/structure details learned from each subnetwork to generate high-quality pseudolabels (PLs) and alleviate error accumulation. Second, a dual self-supervised multiscale consistency (DSMC) loss is presented to both explicitly and implicitly utilize consistency regularization, enabling the promotion of model robustness on multiscale objects and preventing overfitting on false-annotated pixels in noisy PLs. Third, a locally enhanced feature aggregation network is proposed to integrate the multilevel semantic features and alleviate low-level noise interference, producing precise segmentation masks. Extensive evaluation on three RSI datasets demonstrates that the proposed method yields superior performance compared with recent single-stage techniques and several multistage methods, thus revealing its effectiveness and superiority.Keywords
Funding Information
- Beijing Natural Science Foundation (4222046)
- National Natural Science Foundation of China (41771407, 61571050, 62271060)
This publication has 62 references indexed in Scilit:
- End-to-end weakly supervised semantic segmentation with reliable region miningPattern Recognition, 2022
- Learning Self-supervised Low-Rank Network for Single-Stage Weakly and Semi-supervised Semantic SegmentationInternational Journal of Computer Vision, 2022
- Weakly Supervised Semantic Segmentation with Boundary Exploration2020
- Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation2020
- A survey of semi- and weakly supervised semantic segmentation of imagesArtificial Intelligence Review, 2019
- A brief introduction to weakly supervised learningNational Science Review, 2017
- Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation2016
- What’s the Point: Semantic Segmentation with Point Supervision2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015