Search Results for author: Kaixin Chen

Found 4 papers, 3 papers with code

SamplingAug: On the Importance of Patch Sampling Augmentation for Single Image Super-Resolution

1 code implementation30 Nov 2021 Shizun Wang, Ming Lu, Kaixin Chen, Jiaming Liu, Xiaoqi Li, Chuang Zhang, Ming Wu

However, existing methods mostly train the DNNs on uniformly sampled LR-HR patch pairs, which makes them fail to fully exploit informative patches within the image.

Data Augmentation Image Super-Resolution +1

CNNPruner: Pruning Convolutional Neural Networks with Visual Analytics

no code implementations8 Sep 2020 Guan Li, Junpeng Wang, Han-Wei Shen, Kaixin Chen, Guihua Shan, Zhonghua Lu

It considers the importance of convolutional filters through both instability and sensitivity, and allows users to interactively create pruning plans according to a desired goal on model size or accuracy.

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