Anchor Retouching via Model Interaction for Robust Object Detection in Aerial Images

Liang, Dong; Geng, Qixiang; Wei, Zongqi; Vorontsov, Dmitry А.; Kim, Ekaterina L.; Wei, Mingqiang; Zhou, Huiyu

doi:10.1109/tgrs.2021.3136350

Cited by 26 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DOTA-v1.0 Table 4 provides a comprehensive comparison of our method with state-of-the-art approaches on DOTA-v1.0, including CSL (Yang and Yan 2020), R 3 Det (Yang et al 2021a), SASM (Hou et al 2022), ReDet (Han et al 2021), GWD (Yang et al 2021b), DEA (Liang et al 2022), KLD (Yang et al 2021c), Oriented RCNN (O-RCNN) (Xie et al 2021b), KFIoU (Yang et al 2022), RVSA (Wang et al 2022), and RTMDet (Lyu et al 2022). We evaluate STD within Oriented RCNN frameworks (STD-O) and both ViT and HiViT models are used for evaluations.…”

Section: Performance Comparisonmentioning

confidence: 99%

Spatial Transform Decoupling for Oriented Object Detection

Yu,

Tian,

et al. 2024

AAAI

View full text Add to dashboard Cite

Vision Transformers (ViTs) have achieved remarkable success in computer vision tasks. However, their potential in rotation-sensitive scenarios has not been fully explored, and this limitation may be inherently attributed to the lack of spatial invariance in the data-forwarding process. In this study, we present a novel approach, termed Spatial Transform Decoupling (STD), providing a simple-yet-effective solution for oriented object detection with ViTs. Built upon stacked ViT blocks, STD utilizes separate network branches to predict the position, size, and angle of bounding boxes, effectively harnessing the spatial transform potential of ViTs in a divide-and-conquer fashion. Moreover, by aggregating cascaded activation masks (CAMs) computed upon the regressed parameters, STD gradually enhances features within regions of interest (RoIs), which complements the self-attention mechanism. Without bells and whistles, STD achieves state-of-the-art performance on the benchmark datasets including DOTA-v1.0 (82.24% mAP) and HRSC2016 (98.55% mAP), which demonstrates the effectiveness of the proposed method. Source code is available at https://github.com/yuhongtian17/Spatial-Transform-Decoupling.

show abstract

Section: Performance Comparisonmentioning

confidence: 99%

Spatial Transform Decoupling for Oriented Object Detection

Yu,

Tian,

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…Purely unsupervised learning person re-ID. Purely unsupervised learning person re-ID methods completely train models on unlabeled data [ 5 , 6 , 7 , 9 , 10 , 24 , 25 , 26 , 27 , 28 ]. The training process usually consists of four main steps, including clustering to generate pseudo labels, constructing a memory dictionary, computing the contrastive loss, and updating the feature representations.…”

Section: Related Workmentioning

confidence: 99%

Discriminatively Unsupervised Learning Person Re-Identification via Considering Complicated Images

Liang

2023

Sensors

Self Cite

View full text Add to dashboard Cite

State-of-the-art purely unsupervised learning person re-ID methods first cluster all the images into multiple clusters and assign each clustered image a pseudo label based on the cluster result. Then, they construct a memory dictionary that stores all the clustered images, and subsequently train the feature extraction network based on this dictionary. All these methods directly discard the unclustered outliers in the clustering process and train the network only based on the clustered images. The unclustered outliers are complicated images containing different clothes and poses, with low resolution, severe occlusion, and so on, which are common in real-world applications. Therefore, models trained only on clustered images will be less robust and unable to handle complicated images. We construct a memory dictionary that considers complicated images consisting of both clustered and unclustered images, and design a corresponding contrastive loss by considering both kinds of images. The experimental results show that our memory dictionary that considers complicated images and contrastive loss can improve the person re-ID performance, which demonstrates the effectiveness of considering unclustered complicated images in unsupervised person re-ID.

show abstract

“…DEA-net [121] proposed a dynamically improved anchor network to solve the issue of small object labels being easily lost or mislabeled. In order to provide qualifying samples, the network employs sample discriminators to carry out interactive sample screening between anchored and unanchored units.…”

Section: Data Enhancementmentioning

confidence: 99%

Small Object Detection Based on Deep Learning for Remote Sensing: A Comprehensive Review

Wang

Song

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

With the accelerated development of artificial intelligence, remote-sensing image technologies have gained widespread attention in smart cities. In recent years, remote sensing object detection research has focused on detecting and counting small dense objects in large remote sensing scenes. Small object detection, as a branch of object detection, remains a significant challenge in research due to the image resolution, size, number, and orientation of objects, among other factors. This paper examines object detection based on deep learning and its applications for small object detection in remote sensing. This paper aims to provide readers with a thorough comprehension of the research objectives. Specifically, we aggregate the principal datasets and evaluation methods extensively employed in recent remote sensing object detection techniques. We also discuss the irregularity problem of remote sensing image object detection and overview the small object detection methods in remote sensing images. In addition, we select small target detection methods with excellent performance in recent years for experiments and analysis. Finally, the challenges and future work related to small object detection in remote sensing are highlighted.

show abstract

Anchor Retouching via Model Interaction for Robust Object Detection in Aerial Images

Cited by 26 publications

References 39 publications

Spatial Transform Decoupling for Oriented Object Detection

Spatial Transform Decoupling for Oriented Object Detection

Discriminatively Unsupervised Learning Person Re-Identification via Considering Complicated Images

Small Object Detection Based on Deep Learning for Remote Sensing: A Comprehensive Review

Contact Info

Product

Resources

About