G-CNN: Object Detection via Grid Convolutional Neural Network

Lu, Qishuo; Liu, Chonghua; Jiang, Zhuqing; Men, Aidong; Yang, Bo

doi:10.1109/access.2017.2770178

Cited by 29 publications

(19 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are t idle cycles between two ADDRGEN instructions executed. Thus, the real peak computational efficiency is (6). Num vaild_ max is the maximum number of valid addresses included in the ADDRGEN instructions.…”

Section: ) Convolution Kernel Sizementioning

confidence: 99%

See 1 more Smart Citation

LACS: A High-Computational-Efficiency Accelerator for CNNs

Shang

Qian²,

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) have become continually deeper. With the increasing depth of CNNs, the invalid calculations caused by padding-zero operations, filling-zero operations and stride length (stride length>1) represent an increasing proportion of all calculations. To adapt to different CNNs and to eliminate the influences of padding-zero operations, filling-zero operations and stride length on the computational efficiency of the accelerator, we draw upon the computation pattern of CPUs to design an efficient and versatile CNN accelerator, LACS (Loading-Addressing-Computing-Storing). We reduce the amount of data movements between registers and the on-chip buffer from O(k × k) to O(k) by a bypass buffer mechanism. Finally, we deploy LACS on a field-programmable gate array (FPGA) chip and analyze the factors that affect the computational efficiency of LACS. We also run popular CNNs on LACS. The results show that LACS achieves an extremely high computational efficiency, 98.51% when executing AlexNet and 99.66% when executing VGG-16, significantly exceeding state-of-the-art accelerators. INDEX TERMS Accelerator, convolutional neural networks (CNNs), field-programmable gate array (FPGA), buffer mechanism.

show abstract

Section: ) Convolution Kernel Sizementioning

confidence: 99%

“…Convolutional neural networks (CNNs) are widely used in many domains, such as object recognition [1], [2] and detection [3]- [6]. CNNs have become continually deeper for high inference accuracy.…”

Section: Introductionmentioning

confidence: 99%

LACS: A High-Computational-Efficiency Accelerator for CNNs

Shang

Qian²,

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In recent years, deep learning has developed rapidly in the field of computer vision. It has made great progress in image classification [12][13][14][15][16][17][18], object detection [19,20] and image segmentation [22][23][24][25][26][27]. Compared with traditional methods, deep neural networks can automatically extract features from the input data and achieve higher accuracy.…”

Section: Related Workmentioning

confidence: 99%

A Novel Adaptive Weighted Loss Design in Adversarial Learning for Retinal Nerve Fiber Layer Defect Segmentation

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Glaucoma is a chronic eye disease that can cause permanent visual loss and is difficult to detect early. Retinal nerve fiber layer defect (RNFLD) is clinical evidence for the diagnosis of glaucoma. Classical deep learning based methods can be used to segment RNFLD from fundus images. However, the segmentation results of these methods do not have the specific geometry of RNFLD, and the segmentation errors of fundus images with special styles are large. In this paper, we present a novel conditional adversarial shuffle U-shaped network (CASU-Net) to segment RNFLD, which consists of a generator and a discriminator. For the generator, a mixed loss is designed, which consists of an adaptive weighted segmentation loss and an adversarial loss. This adaptive weighted segmentation loss can balance the segmentation accuracy of the target and background region, and assign more attention to the hard samples, thus ensuring the consistent improvement of the segmentation accuracy of all fundus images. The adversarial loss not only helps to improve the pixel-wise segmentation accuracy but also makes the geometry of the RNFLD segmentation closer to the ground truth. In addition, in the generator, a shuffle module was designed to fully mine the information of all channels to improve the feature extraction capability of the model. The proposed CASU-Net is verified on a RNFLD dataset from Beijing Tongren Hospital. The experiments show that the CASU-Net achieves state-of-the-art results on this dataset. INDEX TERMS Glaucoma, retinal nerve fiber layer defect segmentation, deep learning.

show abstract

“…E-mail: maoyao@ioe.ac.cn *Institute of Optics and Electronics, Chinese Academy of Science, Chengdu, 610209, China **Key Laboratory of Optical Engineering, Chinese Academy of Science, Chengdu, 610209, China ***University of Chinese Academy of Science, Beijing, 100039, China neural networks (CNNs) method in an image classification challenge (ILSVRC2012) and obtained striking results, which turned CNN-based methods into the mainstream in the field of computer vision. That aroused a significant class of methods [16][17][18][19][20][21][22][23][24][25][26][27] addressing this problem with the CNN model. Among these approaches, the regions-with-convolutional-neural-network (R-CNN) framework [16] has achieved excellent detection performance and became a commonly employed paradigm for object detection.…”

Section: Introductionmentioning

confidence: 99%

DiagonalNet: Confidence diagonal lines for the UAV detection

Duan

Mao

et al. 2019

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

Due to the maneuverability and small size of the Unmanned aerial vehicles (UAVs), the traditional object detection method cannot meet the requirements of detection accuracy and real‐time performance. To address this dilemma, we propose an object detection method by using the improved hourglass network as its backbone network generating the confidence diagonal lines as detection result, and then getting the bounding box through this diagonal line. As a one‐stage method, it has a good real‐time performance. At the same time, due to the good performance of our improved network, its mean average precision performs well. Through experiments with the UAV dataset, compared with faster‐regions‐with‐convolutional‐neural‐network and You only look once (YOLO), we show that the proposed framework can quickly and accurately detect objects. © 2019 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

show abstract

G-CNN: Object Detection via Grid Convolutional Neural Network

Cited by 29 publications

References 29 publications

LACS: A High-Computational-Efficiency Accelerator for CNNs

LACS: A High-Computational-Efficiency Accelerator for CNNs

A Novel Adaptive Weighted Loss Design in Adversarial Learning for Retinal Nerve Fiber Layer Defect Segmentation

DiagonalNet: Confidence diagonal lines for the UAV detection

Contact Info

Product

Resources

About