Search Results for author: Chengpeng Chen

Found 4 papers, 3 papers with code

RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization

2 code implementations11 Nov 2022 Chengpeng Chen, Zichao Guo, Haien Zeng, Pengfei Xiong, Jian Dong

Experiments on ImageNet and COCO benchmarks demonstrate that the proposed RepGhostNet is much more effective and efficient than GhostNet and MobileNetV3 on mobile devices.

Improving Image Restoration by Revisiting Global Information Aggregation

2 code implementations8 Dec 2021 Xiaojie Chu, Liangyu Chen, Chengpeng Chen, Xin Lu

Our TLC converts global operations to local ones only during inference so that they aggregate features within local spatial regions rather than the entire large images.

Color Image Denoising Deblurring +7

HINet: Half Instance Normalization Network for Image Restoration

2 code implementations13 May 2021 Liangyu Chen, Xin Lu, Jie Zhang, Xiaojie Chu, Chengpeng Chen

Specifically, we present a novel block: Half Instance Normalization Block (HIN Block), to boost the performance of image restoration networks.

Deblurring Image Deblurring +3

Learning Effective RGB-D Representations for Scene Recognition

no code implementations17 Sep 2018 Xinhang Song, Shuqiang Jiang, Luis Herranz, Chengpeng Chen

We show that this limitation can be addressed by using RGB-D videos, where more comprehensive depth information is accumulated as the camera travels across the scene.

Scene Recognition Video Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.