ReFPN-FCOS: One-Stage Object Detection for Feature Learning and Accurate Localization

Zeng, Jian; Xiong, Jiale; Fu, Xiang; Leng, Lu

doi:10.1109/access.2020.3044564

Cited by 10 publications

(3 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To verify the effectiveness of the proposed model, the detection results of the proposed model on MS COCO dataset are compared with four multi-stage methods, including Faster R-CNN [15], Mask RCNN [47], Libra RCNN [48], AutoDet [49], six one-stage methods, including YOLOv3 [50], SSD [29], RefineDet [51], RetinaNet [18], GHM [42], EMCA [53] and five anchor-free methods, including CornerNet [19], FCOS [21], ReFPN-FCOS [54], Pseudo-IoU [54], ObjectBox [56] methods, and the comparison results are shown in Table 1.…”

Section: B Comparisons With State-of-the-art Methodsmentioning

confidence: 99%

An Anchor-Free Lightweight Object Detection Network

Wang,

Gou

2023

IEEE Access

View full text Add to dashboard Cite

Existing anchor-free object detection methods have achieved some amazing results, but these methods are relatively complex and the inference speed is also slow. In this paper, an anchor-free lightweight object detection network is proposed. The proposed method effectively overcomes the limitation of detection model by anchor-free mechanism, and the lightweight backbone network reduces the computational cost. In addition, the proposed small object enhancement module can enhance the focus on small objects, which improves the detection capability of small objects. Besides, a label assignment strategy is proposed to determine the prominent feature, and a center correction mechanism is introduced to make the predicted bounding box closer to the ground truth to further improve the detection accuracy. Extensive experiments are conducted on MS COCO and Pascal VOC datasets, and the results demonstrate that the proposed method achieves better results than the existing detection methods on detection accuracy by increasing 0.5% on the MS COCO dataset, and has a detection accuracy increase of 0.4% on the Pascal VOC dataset, which proves the superiority of the proposed method.

show abstract

Section: B Comparisons With State-of-the-art Methodsmentioning

confidence: 99%

An Anchor-Free Lightweight Object Detection Network

Wang,

Gou

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Liu et al [28] proposed the path aggregation network (PANet), which utilizes the rich location information of the bottom layer to enhance the entire feature hierarchy, shortening the information paths of the top and bottom layers. Zeng et al [29] proposed a refined feature pyramid network. Inspired by the above FPN idea, we propose a multi-scale contextual information aggregation module (CIA) to alleviate the information loss suffered by higher layers due to the reduction of feature channels.…”

Section: Feature Pyramid Networkmentioning

confidence: 99%

“…Zeng et al. [29] proposed a refined feature pyramid network. Inspired by the above FPN idea, we propose a multi‐scale contextual information aggregation module (CIA) to alleviate the information loss suffered by higher layers due to the reduction of feature channels.…”

Section: Related Workmentioning

confidence: 99%

Improved BlendMask: Nuclei instance segmentation for medical microscopy images

Wang

Zhang

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

Nuclei instance segmentation is an important task in medical image analysis involving cell‐level pathological analysis, which is of great significance for many biomedical applications. Nuclei segmentation is a challenging task due to edge adhesions and the distribution of numerous tiny dense nuclei. In this work, a nuclei instance segmentation framework, namely, the improved BlendMask is proposed. In this framework, in order to improve the performance of detection and segmentation of dense small objects and adhering nuclei, two components, including dilated convolution aggregation module (DCA) and context information aggregation module (CIA), are designed. The DCA constructs multi‐path parallel dilated convolution, which greatly increases the receptive field of the network and the ability to capture multi‐scale contextual information. The CIA reduces the information loss in the channel by endowing the network with high‐level multi‐scale spatial context information. In addition, a novel distributional ranking loss function is given that can effectively alleviate the imbalance between the target and the background. The proposed method is validated on the DSB2018 dataset. Compared to BlendMask, this network improves by 3.6% on AP segmentation metric, and the segmentation performance of this network is superior to that of several recent classic open‐source nuclei instance segmentation methods.

show abstract