Extend the shallow part of single shot multibox detector via convolutional neural network

Zheng, Liwen; Fu, Canmiao; Zhao, Yong

doi:10.1117/12.2503001

Cited by 56 publications

(33 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2018, Zhou et al [21] introduced DenseNet-169 [22], a dense convolutional network with better performance than the deep residual network, as the backbone network of SSD and proposed an STDN (Scale-Transferrable Detection Network) approach which achieved the detection accuracy close to the DSSD while improving the detection speed. Also, Jeong et al [23], Lee et al [24], Cao et al [25] and Zheng et al [26] proposed other improved SSD approaches for object detection, but the existing research on the improvements of YOLO series approaches are still less.…”

mentioning

confidence: 99%

DC-SPP-YOLO: Dense connection and spatial pyramid pooling based YOLO for object detection

Huang

Wang

et al. 2020

Information Sciences

293

View full text Add to dashboard Cite

Abstract：Although YOLOv2 approach is extremely fast on object detection; its backbone network has the low ability on feature extraction and fails to make full use of multi-scale local region features, which restricts the improvement of object detection accuracy. Therefore, this paper proposed a DC-SPP-YOLO (Dense Connection and Spatial Pyramid Pooling Based YOLO) approach for ameliorating the object detection accuracy of YOLOv2. Specifically, the dense connection of convolution layers is employed in the backbone network of YOLOv2 to strengthen the feature extraction and alleviate the vanishing-gradient problem. Moreover, an improved spatial pyramid pooling is introduced to pool and concatenate the multi-scale local region features, so that the network can learn the object features more comprehensively. The DC-SPP-YOLO model is established and trained based on a new loss function composed of mean square error and cross entropy, and the object detection is realized. Experiments demonstrate that the mAP (mean Average Precision) of DC-SPP-YOLO proposed on PASCAL VOC datasets and UA-DETRAC datasets is higher than that of YOLOv2; the object detection accuracy of DC-SPP-YOLO is superior to YOLOv2 by strengthening feature extraction and using the multi-scale local region features.

show abstract

mentioning

confidence: 99%

DC-SPP-YOLO: Dense connection and spatial pyramid pooling based YOLO for object detection

Huang

Wang

et al. 2020

Information Sciences

293

View full text Add to dashboard Cite

show abstract

“…SSD [14] discretizes the output space of bounding-boxes into a set of anchors, and the trained network generates the score for the presence of each object category and produces adjustment for each anchor to better match the object location. To further speed up the one-stage detectors and improve the detection performance, some YOLO follow-up works [17], [35] and some SSD subsequent methods [15], [36], [37] have been proposed over the next few years.…”

Section: Related Work a Fully-supervised Object Detectionmentioning

confidence: 99%

Beyond Weakly Supervised: Pseudo Ground Truths Mining for Missing Bounding-Boxes Object Detection

Zhang

Ding

Bai

et al. 2020

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Due to the shortcomings of the weakly-supervised and fully-supervised object detection (i.e. unsatisfactory performance and expensive annotations, respectively), leveraging partially labeled images in a cost-effective way to train an object detector has attracted much attention. In this paper, we formulate this challenging task as a missing bounding-boxes object detection problem. Specifically, we develop a pseudo ground truth mining (PGTM) procedure to automatically find the missing boundingboxes for the unlabeled instances, called pseudo ground truths here, in the training data, and then combine the mined pseudo ground truths and the labeled annotations to train a fullysupervised object detector. Furthermore, we further propose an incremental learning (IL) framework to gradually incorporate the results of the trained fully-supervised detector to improve the performance of missing bounding-boxes object detection. More importantly, we find an effective way to label the massive images with limited labors and funds, which is crucial when building a large-scale weakly/webly labeled dataset for object detection. Extensive experiments on the PASCAL VOC and COCO benchmarks demonstrate that our proposed method can narrow the gap between fully-supervised and weakly-supervised object detectors, and we outperform the previous state-of-the-art weakly-supervised detectors by a large margin (more than 3% mAP absolutely) when the missing rate equals 0.9. Moreover, our proposed method with 30% missing bounding-box annotations can achieve comparable performance to some fully-supervised detectors.

show abstract

“…boxes for Scale 3; (109, 114), (121, 153), and (169, 173) are the anchor boxes for Scale 2; and (232, 214), (241, 203), and (259, 271) are the anchor boxes for Scale 1. The sizes of the anchor boxes for the UCS-AOD dataset are as follows: (19,22), (23,29), (31,38), (49,52), (63, 86), (80, 92), (101, 124), (118, 147), (152, 167), (225, 201), (231, 212), and (268, 279). Among them, (19,22), (23,29), and (31,38) are the anchor boxes for Scale 4; (49, 52), (63, 86), and (80, 92) are the anchor boxes for Scale 3; (101, 124), (118, 147), and (152, 167) are the anchor boxes for Scale 2, and (225, 201), (231, 212), and (268, 279) are the anchor boxes for Scale 1.…”

Section: Anchor Boxes Of Our Modelmentioning

confidence: 99%

MRFF-YOLO: A Multi-Receptive Fields Fusion Network for Remote Sensing Target Detection

Xu¹,

Wu²

2020

Remote Sensing

View full text Add to dashboard Cite

High-altitude remote sensing target detection has problems related to its low precision and low detection rate. In order to enhance the performance of detecting remote sensing targets, a new YOLO (You Only Look Once)-V3-based algorithm was proposed. In our improved YOLO-V3, we introduced the concept of multi-receptive fields to enhance the performance of feature extraction. Therefore, the proposed model was termed Multi-Receptive Fields Fusion YOLO (MRFF-YOLO). In addition, to address the flaws of YOLO-V3 in detecting small targets, we increased the detection layers from three to four. Moreover, in order to avoid gradient fading, the structure of improved DenseNet was chosen in the detection layers. We compared our approach (MRFF-YOLO) with YOLO-V3 and other state-of-the-art target detection algorithms on an Remote Sensing Object Detection (RSOD) dataset and a dataset of Object Detection in Aerial Images (UCS-AOD). With a series of improvements, the mAP (mean average precision) of MRFF-YOLO increased from 77.10% to 88.33% in the RSOD dataset and increased from 75.67% to 90.76% in the UCS-AOD dataset. The leaking detection rates are also greatly reduced, especially for small targets. The experimental results showed that our approach achieved better performance than traditional YOLO-V3 and other state-of-the-art models for remote sensing target detection.

show abstract

Extend the shallow part of single shot multibox detector via convolutional neural network

Cited by 56 publications

References 17 publications

DC-SPP-YOLO: Dense connection and spatial pyramid pooling based YOLO for object detection

DC-SPP-YOLO: Dense connection and spatial pyramid pooling based YOLO for object detection

Beyond Weakly Supervised: Pseudo Ground Truths Mining for Missing Bounding-Boxes Object Detection

MRFF-YOLO: A Multi-Receptive Fields Fusion Network for Remote Sensing Target Detection

Contact Info

Product

Resources

About