An anchor-free object detector with novel corner matching method

Ma, Tingsong; Tian, Wenhong; Kuang, Ping; Xie, Yuanlun

doi:10.1016/j.knosys.2021.107083

Cited by 14 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Duan et al 15 further extended Cornernet by predicting the center point of an object. Ma et al 16 proposed to predict a matching degree score between the predicted bounding box and the ground truth as well as the IoU. Sun et al 17 proposed to a universal relation exploring scheme to explore the relations of different entity level, such as objects, superpixels and pixels.…”

Section: Detection Headsmentioning

confidence: 99%

“…Jiang et al 21 proposed to predict the intersection-over-union(IoU) between the bounding box and the matched ground truth through an IoU-Net. Ma et al 16 proposed to utilize the matching degree score of the corner points between the predicted bounding box and the ground truth to indicate the localization confidence. Mask Scoring R-CNN 22 proposed to predict mask IoU for better segmentation performance based on IoU-Net and Mask R-CNN.…”

Section: Localization Confidence Predictionmentioning

confidence: 99%

See 1 more Smart Citation

Learning High-quality Proposals for Acne Detection

Zhang¹,

Zhang²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Acne detection is crucial for interpretative diagnosis and precise treatment of skin disease. The arbitrary boundary and small size of acne lesions lead to a significant number of poor-quality proposals in two-stage detection. In this paper, we propose a novel head structure for Region Proposal Network to improve the proposals' quality in two ways. At first, a Spatial Aware Double Head(SADH) structure is proposed to disentangle the representation learning for classification and localization from two different spatial perspectives. The proposed SADH ensures a steeper classification confidence gradient and suppresses the proposals having low intersection-over-union(IoU) with the matched ground truth. Then, we propose a Normalized Wasserstein Distance prediction branch to improve the correlation between the proposals' classification scores and IoUs. In addition, to facilitate further research on acne detection, we construct a new dataset named AcneSCU, with high-resolution imageries, precise annotations, and fine-grained lesion categories. Extensive experiments are conducted on both AcneSCU and the public dataset ACNE04, and the results demonstrate the proposed method could improve the proposals' quality, consistently outperforming state-of-the-art approaches. Code and the collected dataset are available in https://github.com/pingguokiller/acnedetection.

show abstract

Section: Detection Headsmentioning

confidence: 99%