BorderDet: Border Feature for Dense Object Detection

Qiu, Han; Ma, Yuchen; Li, Zeming; Liu, Songtao; Sun, Jian

doi:10.1007/978-3-030-58452-8_32

Cited by 126 publications

(52 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, many studies have been performed to encode rotated features better, such as those on RoI transformer [29], DRBox-v2 [43], GWD Loss [44], Gliding vertex [45], S 2 A-Net [46], etc. The anchor-free methods [47][48][49][50] have been given more attention recently. These methods cancel all kinds of hyperparameters of anchors and provide a more concise pipeline for detection.…”

Section: Object Detection In Remote Sensing Imagesmentioning

confidence: 99%

LR-TSDet: Towards Tiny Ship Detection in Low-Resolution Remote Sensing Images

Pan

Lei

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Recently, deep learning-based methods have made great improvements in object detection in remote sensing images (RSIs). However, detecting tiny objects in low-resolution images is still challenging. The features of these objects are not distinguishable enough due to their tiny size and confusing backgrounds and can be easily lost as the network deepens or downsamples. To address these issues, we propose an effective Tiny Ship Detector for Low-Resolution RSIs, abbreviated as LR-TSDet, consisting of three key components: a filtered feature aggregation (FFA) module, a hierarchical-atrous spatial pyramid (HASP) module, and an IoU-Joint loss. The FFA module captures long-range dependencies by calculating the similarity matrix so as to strengthen the responses of instances. The HASP module obtains deep semantic information while maintaining the resolution of feature maps by aggregating four parallel hierarchical-atrous convolution blocks of different dilation rates. The IoU-Joint loss is proposed to alleviate the inconsistency between classification and regression tasks, and guides the network to focus on samples that have both high localization accuracy and high confidence. Furthermore, we introduce a new dataset called GF1-LRSD collected from the Gaofen–1 satellite for tiny ship detection in low-resolution RSIs. The resolution of images is 16m and the mean size of objects is about 10.9 pixels, which are much smaller than public RSI datasets. Extensive experiments on GF1-LRSD and DOTA-Ship show that our method outperforms several competitors, proving its effectiveness and generality.

show abstract

Section: Object Detection In Remote Sensing Imagesmentioning

confidence: 99%

LR-TSDet: Towards Tiny Ship Detection in Low-Resolution Remote Sensing Images

Pan

Lei

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Coordinate attention [38] decomposes attention into one-dimensional vectors along two directions to construct an attention mechanism. BorderDet [39] through experiments, it is found that there may be redundancy in extracting features from all object regions. Therefore, it can reduce the number of calculations that are necessary and can improve the accuracy by extracting the features of the boundary and the center of the object and by enhancing the features.…”

Section: Attention Mechanismmentioning

confidence: 99%

EFM-Net: Feature Extraction and Filtration with Mask Improvement Network for Object Detection in Remote Sensing Images

Wang¹,

Jia²,

Gu³

2021

Remote Sensing

View full text Add to dashboard Cite

Object detection is an essential task in computer vision. Many methods have made significant progress in ordinary object detection. Due to the particularity of remote sensing images, the detection target is tiny, the background is messy, dense, and has mutual occlusion, which makes the general detection method challenging to apply to remote sensing images. For these problems, we propose a new detection framework feature extraction and filtration method with a mask improvement network (EFM-Net) to enhance object detection ability. In EFM-Net, we designed a multi-branched feature extraction (MBFE) module to better capture the information in the feature graph. In order to suppress the background interference, we designed a background filtering module based on attention mechanisms to enhance the attention of objects. Finally, we proposed a mask generate the boundary improvement method to make the network more robust to occlusion detection. We tested the DOTA v1.0, NWPU VHR-10, and UCAS-AOD datasets, and the experimental results show that our method has excellent effects.

show abstract

“…For example, RepPoints [43] uses 9 points to describe a bounding box, and its detection head uses deformable convolution to refine the positions of 9 points twice. The detection heads of BorderDet [44] and VarifocalNet [45] both add some additional processing steps after the FCOS detection head, and make a further feature extraction based on the coarse detection results of FCOS, then make use of the enhanced features for refine prediction. Compared with single-stage detection methods, two-stage detection methods achieve better detection accuracy, but the processing time will also increase.…”

Section: A General Object Detectors Based On Cnnsmentioning

confidence: 99%

Hourglass Face Detector for Hard Face

Yü

Yin

Zhang

et al. 2021

2021 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Face detection is an upstream task of facial image analysis. In many real-world scenarios, we need to detect small, occluded or dense faces that are hard to detect, but hard face detection is a challenging task in particular considering the balance between accuracy and inference speed for real-world applications. This paper proposes an Hourglass Face Detector (HFD) for hard face by developing a deep one-stage fullyconvolutional hourglass network, which achieves an excellent balance between accuracy and inference speed. To this end, the HFD firstly shrinks a feature map by a series of stridden convolutional layers rather than pooling layers, so that useful subtle information is preserved better. Secondly, it exploits context information by merging fine-grained shallow feature maps with deep ones full of semantic information, making a better fusion of detailed information and semantic information to achieve a better detection of small faces. Moreover, the HFD exploits prior and multiscale information from the training data to enhance its scale-invariance and adaptability of anchor scales. Compared with the SSH and S 3 FD methods, the HFD can achieve a better performance in average precision on detecting hard faces as well as a quicker inference. Experiments on the WIDER FACE and FDDB datasets demonstrate the superior performance of our proposed method.

show abstract

BorderDet: Border Feature for Dense Object Detection

Cited by 126 publications

References 22 publications

LR-TSDet: Towards Tiny Ship Detection in Low-Resolution Remote Sensing Images

LR-TSDet: Towards Tiny Ship Detection in Low-Resolution Remote Sensing Images

EFM-Net: Feature Extraction and Filtration with Mask Improvement Network for Object Detection in Remote Sensing Images

Hourglass Face Detector for Hard Face

Contact Info

Product

Resources

About