Coordinate-based anchor-free module for object detection

Tang, Zhiyong; Yang, Jianbing; Pei, Zhongcai; Song, Xiao

doi:10.1007/s10489-021-02373-8

Cited by 10 publications

(3 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Keypoint detection technology has been widely used in computer vision research, such as human pose detection tasks (Geng et al, 2021; Jiang et al, 2021; Zhang, Chen, & Tao, 2021) and anchor free object detection tasks (Liu, Li, et al, 2021; Tang et al, 2021; Zhou, Wang, & Krähenbühl, 2019; Zhou, Zhuo, & Krahenbuhl, 2019). The human body keypoint estimation task is to detect

k

2D keypoints of the human body, such as joints, facial features and so forth and describe human bone information by these keypoints.…”

Section: Related Workmentioning

confidence: 99%

Joint object contour points and semantics for instance segmentation

Zhang,

Fu,

Zhu

et al. 2023

Expert Systems

View full text Add to dashboard Cite

The edges of objects are of great significance to the task of instance segmentation. However, most of the current popular deep neural networks do not pay much attention to the object edge information. More importantly, using the down‐sampling pooling layer in the deep learning network, the edge detail information of the object will be lost. To address this issue, inspired by the manual annotation process, we propose Mask Point R‐CNN aiming at promoting the neural network's attention to the object boundary. Specifically, we introduce the auxiliary task of object contour point detection on the Mask R‐CNN framework, which can effectively improve the gradient flow between different tasks by multi‐task learning and repairing objects' boundary information via feature fusion. Consequently, the model can be more sensitive to the edges of the object and capture more geometric features. Quantitatively, the experimental results show that our Mask Point R‐CNN outperforms vanilla Mask R‐CNN by 3.8% on the Cityscapes dataset and 0.8% on the COCO dataset.

show abstract

k

2D keypoints of the human body, such as joints, facial features and so forth and describe human bone information by these keypoints.…”

Section: Related Workmentioning

confidence: 99%

Joint object contour points and semantics for instance segmentation

Zhang,

Fu,

Zhu

et al. 2023

Expert Systems

View full text Add to dashboard Cite

show abstract

“…We stack the multiple modules of dual attention to further improve the performance. As shown in Figure 4a, the classification branch commonly used in existing algorithms [44] is a fully convolutional network, which consists of four standard convolutional layers with the last one for score calculation. We replace the first three standard 3 × 3 convolutional layers with the three stacked dual attention modules, constituting a new classification branch, as shown in Figure 4b.…”

Section: Adaptive Weight Assignment Based On Dual Attentionmentioning

confidence: 99%

Improved Dual Attention for Anchor-Free Object Detection

Xiang

Zhao

et al. 2022

Sensors

View full text Add to dashboard Cite

In anchor-free object detection, the center regions of bounding boxes are often highly weighted to enhance detection quality. However, the central area may become less significant in some situations. In this paper, we propose a novel dual attention-based approach for the adaptive weight assignment within bounding boxes. The proposed improved dual attention mechanism allows us to thoroughly untie spatial and channel attention and resolve the confusion issue, thus it becomes easier to obtain the proper attention weights. Specifically, we build an end-to-end network consisting of backbone, feature pyramid, adaptive weight assignment based on dual attention, regression, and classification. In the adaptive weight assignment module based on dual attention, a parallel framework with the depthwise convolution for spatial attention and the 1D convolution for channel attention is applied. The depthwise convolution, instead of standard convolution, helps prevent the interference between spatial and channel attention. The 1D convolution, instead of fully connected layer, is experimentally proved to be both efficient and effective. With the adaptive and proper attention, the correctness of object detection can be further improved. On public MS-COCO dataset, our approach obtains an average precision of 52.7%, achieving a great increment compared with other anchor-free object detectors.

show abstract

“…Considering that the traditional anchor-based object detection algorithm applies to pedestrian detection, it is challenging to set targeted anchor hyperparameters, and positive and negative samples are not balanced (Zou et al , 2021; Liu et al , 2020; Tang et al , 2021; Li et al , 2021a, b). In addition, the one-stage object detection algorithm has the advantages of high speed, high detection accuracy, and easy deployment.…”

Section: Introductionmentioning

confidence: 99%

Research on pedestrian detection based on multi-level fine-grained YOLOX algorithm

Wang

Xie

Tian

et al. 2022

IJICC

View full text Add to dashboard Cite

PurposeThe purpose of the study is to address the problems of low accuracy and missed detection of occluded pedestrians and small target pedestrians when using the YOLOX general object detection algorithm for pedestrian detection. This study proposes a multi-level fine-grained YOLOX pedestrian detection algorithm.Design/methodology/approachFirst, to address the problem of the original YOLOX algorithm in obtaining a single perceptual field for the feature map before feature fusion, this study improves the PAFPN structure by adding the ResCoT module to increase the diversity of the perceptual field of the feature map and divides the pedestrian multi-scale features into finer granularity. Second, for the CSPLayer of the PAFPN, a weight gain-based normalization-based attention module (NAM) is proposed to make the model pay more attention to the context information when extracting pedestrian features and highlight the salient features of pedestrians. Finally, the authors experimentally determined the optimal values for the confidence loss function.FindingsThe experimental results show that, compared with the original YOLOX algorithm, the AP of the improved algorithm increased by 2.90%, the Recall increased by 3.57%, and F1 increased by 2% on the pedestrian dataset.Research limitations/implicationsThe multi-level fine-grained YOLOX pedestrian detection algorithm can effectively improve the detection of occluded pedestrians and small target pedestrians.Originality/valueThe authors introduce a multi-level fine-grained ResCoT module and a weight gain-based NAM attention module.

show abstract

Coordinate-based anchor-free module for object detection

Cited by 10 publications

References 43 publications

Joint object contour points and semantics for instance segmentation

Joint object contour points and semantics for instance segmentation

Improved Dual Attention for Anchor-Free Object Detection

Research on pedestrian detection based on multi-level fine-grained YOLOX algorithm

Contact Info

Product

Resources

About