most citedNAT: Neural Architecture Transformer for Accurate and Compact Architectures

72 citations · 144 across the 4 of their papers we have counts for

collaborators

6 papers

cs.CV202068 cited

Attention-guided Context Feature Pyramid Network for Object Detection

Junxu Cao, Qi Chen, Jun Guo +1

For object detection, how to address the contradictory requirement between feature map resolution and receptive field on high-resolution inputs still remains an open question. In t…

eess.IV2020

A Thorough Comparison Study on Adversarial Attacks and Defenses for Common Thorax Disease Classification in Chest X-rays

Chendi Rao, Jiezhang Cao, Runhao Zeng +4

Recently, deep neural networks (DNNs) have made great progress on automated diagnosis with chest X-rays images. However, DNNs are vulnerable to adversarial examples, which may caus…

cs.CV2020

Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution

Yong Guo, Jian Chen, Jingdong Wang +5

Deep neural networks have exhibited promising performance in image super-resolution (SR) by learning a nonlinear mapping function from low-resolution (LR) images to high-resolution…

cs.CV20202 cited

Intelligent Home 3D: Automatic 3D-House Design from Linguistic Descriptions Only

Qi Chen, Qi Wu, Rui Tang +3

Home design is a complex task that normally requires architects to finish with their professional skills and tools. It will be fascinating that if one can produce a house plan intu…

cs.LG201972 cited

NAT: Neural Architecture Transformer for Accurate and Compact Architectures

Yong Guo, Yin Zheng, Mingkui Tan +4

Designing effective architectures is one of the key factors behind the success of deep neural networks. Existing deep architectures are either manually designed or automatically se…

cs.CV20192 cited

Auto-Embedding Generative Adversarial Networks for High Resolution Image Synthesis

Yong Guo, Qi Chen, Jian Chen +3

Generating images via the generative adversarial network (GAN) has attracted much attention recently. However, most of the existing GAN-based methods can only produce low-resolutio…