RepPoints: Point Set Representation for Object Detection

Yang, Ze; Liu, Shaohui; Hu, Han; Wang, Liwei; Lin, Stephen

doi:10.1109/iccv.2019.00975

Cited by 813 publications

(438 citation statements)

References 40 publications

(113 reference statements)

Supporting

Mentioning

434

Contrasting

Unclassified

Order By: Relevance

“…The deformable convolution learns the sampling offsets to enforce it to focus more on the interesting targets. In the object detection task, it has been proved to be effective in improving the localization ability of the network [37,51]. The structure of AFFB is shown in Figure 3.…”

Section: Attention-based Feature Fusion Blockmentioning

confidence: 99%

“…Tian et al [36] encode the target position by predicting 4D vectors pixel by pixel to achieve anchor-free detection. Yang et al [37] use deformable convolution to predict a group of key points for each target. The location of the target is acquired according to the minimum bounding box of the key points.…”

Section: Introductionmentioning

confidence: 99%

“…Reppoints [37]: Reppoints is also a newly proposed anchor-free detection algorithm, which locates a target by predicting a set of key points and transforming them into the predicted bounding box.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Anchor-free Convolutional Network with Dense Attention Feature Aggregation for Ship Detection in SAR Images

Gao

Wang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

In recent years, with the improvement of synthetic aperture radar (SAR) imaging resolution, it is urgent to develop methods with higher accuracy and faster speed for ship detection in high-resolution SAR images. Among all kinds of methods, deep-learning-based algorithms bring promising performance due to end-to-end detection and automated feature extraction. However, several challenges still exist: (1) standard deep learning detectors based on anchors have certain unsolved problems, such as tuning of anchor-related parameters, scale-variation and high computational costs. (2) SAR data is huge but the labeled data is relatively small, which may lead to overfitting in training. (3) To improve detection speed, deep learning detectors generally detect targets based on low-resolution features, which may cause missed detections for small targets. In order to address the above problems, an anchor-free convolutional network with dense attention feature aggregation is proposed in this paper. Firstly, we use a lightweight feature extractor to extract multiscale ship features. The inverted residual blocks with depth-wise separable convolution reduce the network parameters and improve the detection speed. Secondly, a novel feature aggregation scheme called dense attention feature aggregation (DAFA) is proposed to obtain a high-resolution feature map with multiscale information. By combining the multiscale features through dense connections and iterative fusions, DAFA improves the generalization performance of the network. In addition, an attention block, namely spatial and channel squeeze and excitation (SCSE) block is embedded in the upsampling process of DAFA to enhance the salient features of the target and suppress the background clutters. Third, an anchor-free detector, which is a center-point-based ship predictor (CSP), is adopted in this paper. CSP regresses the ship centers and ship sizes simultaneously on the high-resolution feature map to implement anchor-free and nonmaximum suppression (NMS)-free ship detection. The experiments on the AirSARShip-1.0 dataset demonstrate the effectiveness of our method. The results show that the proposed method outperforms several mainstream detection algorithms in both accuracy and speed.

show abstract

Section: Attention-based Feature Fusion Blockmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Anchor-free Convolutional Network with Dense Attention Feature Aggregation for Ship Detection in SAR Images

Gao

Wang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Most prominent architectures that unify both detection and recognition of objects are Mask R-CNN [33], Retina-Net [34], [35], SSD (Single Shot Detector) [36], YOLO [37]- [40], and EfficcientDet [41]. Different anchor-free object detection approaches were introduced: RepPoint network [42], where representative points are learned to arrange themselves in the manner of object's bounds; CenterNet [43], where triplets are detected to improve localization; CornerNet [44], where keypoints are detected; and FCOS [45] as a fully convolutional one-stage detector. Most recently, Detection Transformer (DETR) [46] method encodes prior knowledge about the object detection task, removing the necessity for nonmaxima suppression or anchors.…”

Section: Fast Object Detectionmentioning

confidence: 99%

Neural-Network-Based Traffic Sign Detection and Recognition in High-Definition Images Using Region Focusing and Parallelization

et al. 2020

View full text Add to dashboard Cite

A. Avramović and D. Sluga contributed equally and share the first authorship. This research was partially funded by Ministry of Scientific and Technological Development, Higher Education and Information Society of Republic of Srpska, under contract number 07.051/68-14/18 and contract number 19/6-020/961-144/18, partially under the Bilateral Academic and Technological cooperation between Bosnia and Herzegovina and Slovenia, under contract number 19-6-020/964-25-1/18, and partially by the Slovenian Research Agency under Grant P2-0241 and Grant BI-BA/19-20-047 (Bilateral Collaboration Project).

show abstract

“…Based on the fused feature maps, the object is represented by proposals in anchor based methods [4,25,33] or keypoints in anchor-free methods [19,44,52]. Anchor based methods exploit the global appearance information of the object, relying on pre-defined anchors.…”

Section: Introductionmentioning

confidence: 99%

Guided Attention Network for Object Detection and Counting on Drones

Cai

Zhang

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Object detection and counting are related but challenging problems, especially for drone based scenes with small objects and cluttered background. In this paper, we propose a new Guided Attention network (GAnet) to deal with both object detection and counting tasks based on the feature pyramid. Different from the previous methods relying on unsupervised attention modules, we fuse different scales of feature maps by using the proposed weakly-supervised Background Attention (BA) between the background and objects for more semantic feature representation. Then, the Foreground Attention (FA) module is developed to consider both global and local appearance of the object to facilitate accurate localization. Moreover, the new data argumentation strategy is designed to train a robust model in the drone based scenes with various illumination conditions. Extensive experiments on three challenging benchmarks (i.e., UAVDT, CARPK and PUCPR+) show the state-of-the-art detection and counting performance of the proposed method compared with existing methods. Code can be found at https://isrc.iscas.ac.cn/gitlab/research/ganet.

show abstract

RepPoints: Point Set Representation for Object Detection

Cited by 813 publications

References 40 publications

Anchor-free Convolutional Network with Dense Attention Feature Aggregation for Ship Detection in SAR Images

Anchor-free Convolutional Network with Dense Attention Feature Aggregation for Ship Detection in SAR Images

Neural-Network-Based Traffic Sign Detection and Recognition in High-Definition Images Using Region Focusing and Parallelization

Guided Attention Network for Object Detection and Counting on Drones

Contact Info

Product

Resources

About