ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks

Ding, Xiaohan; Guo, Yuchen; Ding, Guiguang; Han, Jungong

doi:10.1109/iccv.2019.00200

Cited by 624 publications

(325 citation statements)

References 23 publications

Supporting

Mentioning

324

Contrasting

Order By: Relevance

“…qiushizai 56.72 (12) 0.99752 (11) 0.17 GTX 1080 Ti PyTorch self ensemble L 1 , DCT NoahDn matteomaggioni 56.47 (13) 0.99749 (14) 3.54 Tesla V100 TensorFlow flip/rotate (×8) L 1 Dahua isp -56.20 (14) 0.99749 (13) ? GTX 2080 PyTorch ?…”

Section: Challenge Resultsmentioning

confidence: 99%

See 1 more Smart Citation

NTIRE 2019 Challenge on Real Image Denoising: Methods and Results

Abdelhamed

Timofte²,

Brown³

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

This paper reviews the NTIRE 2020 challenge on real image denoising with focus on the newly introduced dataset, the proposed methods and their results. The challenge is a new version of the previous NTIRE 2019 challenge on real image denoising that was based on the SIDD benchmark. This challenge is based on a newly collected validation and testing image datasets, and hence, named SIDD+. This challenge has two tracks for quantitatively evaluating image denoising performance in (1) the Bayer-pattern rawRGB and (2) the standard RGB (sRGB) color spaces. Each track ∼250 registered participants. A total of 22 teams, proposing 24 methods, competed in the final phase of the challenge. The proposed methods by the participating teams represent the current state-of-the-art performance in image denoising targeting real noisy images. The newly collected SIDD+ datasets are publicly available at: https://bit.ly/siddplus_data. A. Abdelhamed (kamel@eecs.yorku.ca, York University), M. Afifi, R. Timofte, and M.S. Brown are the NTIRE 2020 challenge organizers, while the other authors participated in the challenge. Appendix A contains the authors' teams and affiliations. NTIRE webpage: arXiv:2005.04117v1 [cs.CV] 8 May 2020

show abstract

Section: Challenge Resultsmentioning

confidence: 99%

“…Couger AI 2 priyakansal 31.61 (12) 0.9383 (12) 0.23 GTX 1080 Keras/Tensorflow None MSE/SSIM EWHA-AIBI 2 jaayeon 31.38 (13) 0.9417 (10) ?…”

Section: Rtx 2080timentioning

confidence: 99%

NTIRE 2019 Challenge on Real Image Denoising: Methods and Results

Abdelhamed

Timofte²,

Brown³

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

show abstract

“…Feature Pyramid Network (FPN) [14] is an effective method to extract multi-scale feature information from a single image. In order to obtain distinguished feature representation of FPN for geospatial objects, Asymmetric Convolution Block (AC Block) [38] is employed after the output of each scale. Furthermore, we integrate simultaneously the multi-scale feature maps into a discriminative feature map with appropriate size, the integrated feature possesses balanced information from each spatial resolution, which is key for scale variations in aerial images.…”

Section: Multi-scale Feature Integration Network (Mfin)mentioning

confidence: 99%

Multi-Scale Feature Integrated Attention-Based Rotation Network for Object Detection in VHR Aerial Images

Yang

et al. 2020

Sensors

View full text Add to dashboard Cite

Accurate and robust detection of multi-class objects in very high resolution (VHR) aerial images has been playing a significant role in many real-world applications. The traditional detection methods have made remarkable progresses with horizontal bounding boxes (HBBs) due to CNNs. However, HBB detection methods still exhibit limitations including the missed detection and the redundant detection regions, especially for densely-distributed and strip-like objects. Besides, large scale variations and diverse background also bring in many challenges. Aiming to address these problems, an effective region-based object detection framework named Multi-scale Feature Integration Attention Rotation Network (MFIAR-Net) is proposed for aerial images with oriented bounding boxes (OBBs), which promotes the integration of the inherent multi-scale pyramid features to generate a discriminative feature map. Meanwhile, the double-path feature attention network supervised by the mask information of ground truth is introduced to guide the network to focus on object regions and suppress the irrelevant noise. To boost the rotation regression and classification performance, we present a robust Rotation Detection Network, which can generate efficient OBB representation. Extensive experiments and comprehensive evaluations on two publicly available datasets demonstrate the effectiveness of the proposed framework.

show abstract

“…A single branch of ACSE networks consists of 34 layers of ACSE units. And ACSE units own asymmetric convolution (AC) block [19] and Squeeze-and-Excitation (SE) block [20]. AC block uses one-dimension (1-D) asymmetric convolution kernels to enhance the square convolution kernels (typically 3 × 3 kernels).…”

Section: A the Structure Of A Single Branch Acse Networkmentioning

confidence: 99%

Automatic Modulation Recognition for Radar Signals via Multi-Branch ACSE Networks

Wei

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Automatic modulation recognition (AMR) for radar signals plays a significant role in electronic warfare. Conventional recognition methods may suffer from the recognition accuracy and the computation complexity under low signal-to-noise ratio (SNR) conditions. In this paper, a novel multi-branch Asymmetric Convolution Squeeze-and-Excitation (ACSE) networks using multi-domain features and fusion strategy based on a support vector machine is proposed to recognize eight kinds of radar signals. First, features of radar signals in the frequency domain, the autocorrelation domain, and the time-frequency domain are extracted. Then the obtained multi-domain features are converted as the input of the proposed networks which owns the representational power and learning ability. Finally, the outputs of multi-branch ACSE networks are fused via the fusion strategy to obtain the final results. Via simulations, the robustness and effectiveness of the fusion strategy are verified. The results on the simulation dataset prove that the proposed method can achieve more than 93% accuracy at-10dB for all modulations. Compared with four newly proposed networks, the multi-branch ACSE networks achieves better performance under low SNR conditions. And the results on measured signals show that the proposed method outperforms other comparison methods, especially for binary frequency-shift keying (BFSK) signals. INDEX TERMS Automatic modulation recognition, convolutional neural networks, radar signal, neural network application.

show abstract

ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks

Cited by 624 publications

References 23 publications

NTIRE 2019 Challenge on Real Image Denoising: Methods and Results

NTIRE 2019 Challenge on Real Image Denoising: Methods and Results

Multi-Scale Feature Integrated Attention-Based Rotation Network for Object Detection in VHR Aerial Images

Automatic Modulation Recognition for Radar Signals via Multi-Branch ACSE Networks

Contact Info

Product

Resources

About