CE-FPN: enhancing channel information for object detection

Luo, Yihao; Cao, Xiang; Zhang, Juntao; Guo, Jingjuan; Shen, Haibo; Wang, Tianjiang; Feng, Qianjin

doi:10.1007/s11042-022-11940-1

Cited by 102 publications

(46 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FPN structure [22] has an aliasing effect in cross-scale fusion. Multi-scale fusion and cross-layer connection are widely used to improve model performance.…”

Section: E Attention Detection Head Modulementioning

confidence: 99%

Faster Light Detection Algorithm of Traffic Signs Based on YOLOv5s-A2

Kuerban

Chen

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Traffic sign recognition systems have been applied to advanced driving assistance and automatic driving systems to help drivers obtain important road information accurately. The current mainstream detection methods have high accuracy in this task, but the number of model parameters is large, and the detection speed is slow. Based on YOLOv5s as the basic framework, this paper proposes YOLOv5S-A2, which can improve the detection speed and reduce the model size at the cost of reducing the detection accuracy. Firstly, a data augmentation strategy is proposed by combining various operations to alleviate the problem of unbalanced class instances. Secondly, we proposed a path aggregation module of Feature Pyramid Network (FPN) to make new horizontal connections. It can enhance multi-scale feature representation capability and compensate for the loss of feature information. Thirdly, an attention detection head module is proposed to solve the aliasing effect in cross-scale fusion and enhance the representation of predictive features. Experiments on Tsinghua-Tencent 100K dataset (TT100K) show that our method can achieve more remarkable performance improvement and faster inference speed than other advanced technologies. Our method achieves 87.3% mean average precision (mAP) surpassing the original model's 7.9%, and the frames per second (FPS) value is maintained at 87.7. To show generality, we tested it on the German Traffic Sign Detection Benchmark (GTSDB) without tuning and obtained an average precision of 94.1%, and the FPS value is maintained at about 105.3. In addition, the number of YOLOv5s-A2 parameters is about 7.9 M.

show abstract

“…FPN structure [22] has an aliasing effect in cross-scale fusion. Multi-scale fusion and cross-layer connection are widely used to improve model performance.…”

Section: E Attention Detection Head Modulementioning

confidence: 99%

Faster Light Detection Algorithm of Traffic Signs Based on YOLOv5s-A2

Kuerban

Chen

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Widely used feature fusion and feature enhancement methods include the integration of feature maps extracted by different convolution layers(e.g., D-DETR [9], NAS-FPN [10], and Qu [11]) and rich semantic information of feature maps through semantic segmentation branching and global activation module(DES [12] and FCOS [13]). CE-FPN [14], D-DETR [9], and AugFPN [15] are aimed at the problem of low detection accuracy of multi-scale objects. CBNet [16] integrates high-resolution and low-resolution features from different backbone networks.…”

Section: A Feature Blendingmentioning

confidence: 99%

“…Many scholars have used the FPN [17] as the core to build object detection models, including Ren [18], to combine the FPN and SSD. Inspired by the subpixel FCOS [13] to obtain more semantic information, AugFPN [15] makes the most use of multi-scale features, NAS-FPN [10] fuses features from different regions, and CE-FPN [14] outputs information across scales.…”

Section: A Feature Blendingmentioning

confidence: 99%

Ganster R-CNN: Occluded Object Detection Network Based on Generative Adversarial Nets and Faster R-CNN

2022

View full text Add to dashboard Cite

show abstract

“…However, such methods may require repeated computation of features, resulting in higher computation and memory requirements. In addition, multi-scale feature fusion [ 20 , 21 ] enriches difficulty discerning object feature representations by integrating deep and shallow features while adding less computational cost. The other line of effort aims to expand the receptive field using stacking atrous convolutions with different atrous rates or convolutional filters with different sizes [ 22 , 23 ], which is also an effective way to improve object detection performance.…”

Section: Introductionmentioning

confidence: 99%

Scale Enhancement Pyramid Network for Small Object Detection from UAV Images

Sun

Gao²,

Wang³

et al. 2022

Entropy

View full text Add to dashboard Cite

Object detection is challenging in large-scale images captured by unmanned aerial vehicles (UAVs), especially when detecting small objects with significant scale variation. Most solutions employ the fusion of different scale features by building multi-scale feature pyramids to ensure that the detail and semantic information are abundant. Although feature fusion benefits object detection, it still requires the long-range dependencies information necessary for small objects with significant scale variation detection. We propose a simple yet effective scale enhancement pyramid network (SEPNet) to address these problems. A SEPNet consists of a context enhancement module (CEM) and feature alignment module (FAM). Technically, the CEM combines multi-scale atrous convolution and multi-branch grouped convolution to model global relationships. Additionally, it enhances object feature representation, preventing features with lost spatial information from flowing into the feature pyramid network (FPN). The FAM adaptively learns offsets of pixels to preserve feature consistency. The FAM aims to adjust the location of sampling points in the convolutional kernel, effectively alleviating information conflict caused by the fusion of adjacent features. Results indicate that the SEPNet achieves an AP score of 18.9% on VisDrone, which is 7.1% higher than the AP score of state-of-the-art detectors RetinaNet achieves an AP score of 81.5% on PASCAL VOC.

show abstract

CE-FPN: enhancing channel information for object detection

Cited by 102 publications

References 50 publications

Faster Light Detection Algorithm of Traffic Signs Based on YOLOv5s-A2

Faster Light Detection Algorithm of Traffic Signs Based on YOLOv5s-A2

Ganster R-CNN: Occluded Object Detection Network Based on Generative Adversarial Nets and Faster R-CNN

Scale Enhancement Pyramid Network for Small Object Detection from UAV Images

Contact Info

Product

Resources

About