Few-Shot Object Detection on Remote Sensing Images

Li, Xiang; Deng, Jingyu; Fang, Yi

doi:10.1109/tgrs.2021.3051383

Cited by 64 publications

(75 citation statements)

References 136 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the lack of source code and the limitations of our experimental equipment, we directly quote the results of FSODM and the original feature reweighting method FR from the work [19]. Because it does not conduct the 1-shot and 2-shot experiments on the NWPU VHR-10 dataset, we do not list them in the table either.…”

Section: Resultsmentioning

confidence: 99%

“…FR: FR [18] is the first few-shot object detection method based on YOLOv2 [4], which proposed a meta-learning module named feature reweighting. It is re-implemented on remote sensing images by the work [19].…”

Section: Comparing Methodsmentioning

confidence: 99%

“…FSODM: To prove the excellence of our method, we also compare our method with the current state-of-the-art few-shot object detector based on the feature reweighting module in the remote sensing field named FSODM [19].…”

Section: Comparing Methodsmentioning

confidence: 99%

“…To evaluate the detection performance on novel classes, we follow the same division on base and novel classes according to the existing work [19], i.e., 3 novel classes (airplane, baseball diamond, and tennis court) in NWPU VHR-10, and 5 novel classes (airplane, baseball field, tennis court, train station, and windmill) in DIOR. On the NWPU VHR-10 dataset, we base-train on all images that do not contain any object of novel classes, and then randomly select a very small train set containing both base and novel classes for finetuning, in which each class only has K-annotated images, where K equals 1, 2, 3, 5 and 10.…”

Section: Implementation Detailsmentioning

confidence: 99%

See 3 more Smart Citations

Few-Shot Object Detection on Remote Sensing Images via Shared Attention Module and Balanced Fine-Tuning Strategy

Huang

Tang

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Few-shot object detection is a recently emerging branch in the field of computer vision. Recent research studies have proposed several effective methods for object detection with few samples. However, their performances are limited when applied to remote sensing images. In this article, we specifically analyze the characteristics of remote sensing images and propose a few-shot fine-tuning network with a shared attention module (SAM) to adapt to detecting remote sensing objects, which have large size variations. In our SAM, multi-attention maps are computed in the base training stage and shared with the feature extractor in the few-shot fine-tuning stage as prior knowledge to help better locate novel class objects with few samples. Moreover, we design a new few-shot fine-tuning stage with a balanced fine-tuning strategy (BFS), which helps in mitigating the severe imbalance between the number of novel class samples and base class samples caused by the few-shot settings to improve the classification accuracy. We have conducted experiments on two remote sensing datasets (NWPU VHR-10 and DIOR), and the excellent results demonstrate that our method makes full use of the advantages of few-shot learning and the characteristics of remote sensing images to enhance the few-shot detection performance.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Comparing Methodsmentioning

confidence: 99%

Section: Comparing Methodsmentioning

confidence: 99%

Section: Implementation Detailsmentioning

confidence: 99%

See 2 more Smart Citations

Few-Shot Object Detection on Remote Sensing Images via Shared Attention Module and Balanced Fine-Tuning Strategy

Huang

Tang

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Such a problem will become more serious when training deep learning based methods with few images. Although methods designing networks requiring fewer images to train are also proposed [20], abundant samples seems still necessary for accurately detecting specific change areas.…”

Section: Introductionmentioning

confidence: 99%

Deep Siamese Networks Based Change Detection with Remote Sensing Images

et al. 2021

View full text Add to dashboard Cite

Although considerable success has been achieved in change detection on optical remote sensing images, accurate detection of specific changes is still challenging. Due to the diversity and complexity of the ground surface changes and the increasing demand for detecting changes that require high-level semantics, we have to resort to deep learning techniques to extract the intrinsic representations of changed areas. However, one key problem for developing deep learning metho for detecting specific change areas is the limitation of annotated data. In this paper, we collect a change detection dataset with 862 labeled image pairs, where the urban construction-related changes are labeled. Further, we propose a supervised change detection method based on a deep siamese semantic segmentation network to handle the proposed data effectively. The novelty of the method is that the proposed siamese network treats the change detection problem as a binary semantic segmentation task and learns to extract features from the image pairs directly. The siamese architecture as well as the elaborately designed semantic segmentation networks significantly improve the performance on change detection tasks. Experimental results demonstrate the promising performance of the proposed network compared to existing approaches.

show abstract