Weakly Supervised Part-Based Method for Combined Object Detection in Remote Sensing Imagery
Open Access
- 6 June 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 15 (19391404) , 5024-5036
Abstract
Deep learning methods have reached considerable achievement on remote sensing object detection in recent years. However, most methods are designed for single object detection, such as vehicles and ships, and have limited detection capabilities for the combined object with large scale and complex part structure. In this article, we propose a part-based topology distillation network (PTDNet) for accurate and efficient combined object detection in remote sensing imagery. Specifically, a part-based feature module is designed to extract the key parts information of a combined object in a weakly supervised manner. Besides, to balance the accuracy and efficiency of the model, with considering the topology structure of multiple parts in combined objects, a lightweight network training method based on partial topological feature distillation is proposed to improve the model performance without additional parameters. Experiments show that the PTDNet outperforms the state of the art methods and achieves 65.4% mean average precision and 84.1% accuracy for combined object detection.Keywords
Funding Information
- National Natural Science Foundation of China (62171436)
This publication has 46 references indexed in Scilit:
- Scalable Algorithms for Multi-Instance LearningIEEE Transactions on Neural Networks and Learning Systems, 2016
- Active Learning by Querying Informative and Representative ExamplesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- DeepReID: Deep Filter Pairing Neural Network for Person Re-identification2014
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Classification in the Presence of Label Noise: A SurveyIEEE Transactions on Neural Networks and Learning Systems, 2013
- Multiple instance classification: Review, taxonomy and comparative studyArtificial Intelligence, 2013
- A review of multi-instance learning assumptionsThe Knowledge Engineering Review, 2010
- Active learning using pre-clustering2004
- Support-vector networksMachine Learning, 1995
- Least squares quantization in PCMIEEE Transactions on Information Theory, 1982