Yanting Pei
Beijing Jiaotong University
11 Papers
17 Citations
Yanting Pei is an academic researcher from Beijing Jiaotong University. The author has contributed to research in topics: Contextual image classification & Computer science. The author has an hindex of 6, co-authored 9 publications.
Chat about Author
Papers
Effects of Image Degradation and Degradation Removal to CNN-Based Image Classification
TL;DR: Whether image classification performance drops with each kind of degradation, whether this drop can be avoided by including degraded images into training, and whether existing computer vision algorithms that attempt to remove such degradations can help improve the image classificationperformance are studied.
238
Does Haze Removal Help CNN-Based Image Classification?
Yanting Pei,Yaping Huang,Qi Zou,Yuhang Lu,Song Wang +4 more
- 08 Sep 2018
TL;DR: From the experimental results, it is found that the existing image-dehazing methods cannot improve much the image-classification performance and sometimes even reduce the image’s performance.
Degraded Image Semantic Segmentation With Dense-Gram Networks
TL;DR: A novel Dense-Gram Network is proposed to more effectively reduce the gap than the conventional strategies and segment degraded images and yields state-of-the-art semantic segmentation performance on degraded images synthesized using PASCAL VOC 2012, SUNRGBD, CamVid, and CityScapes datasets.
63
A Hybrid convolutional neural network for sketch recognition
TL;DR: This paper proposes a novel architecture, named Hybrid CNN, which is composed of A-Net and S-Net, which describe appearance information and shape information, respectively and demonstrates that the Hybrid CNN achieves competitive accuracy compared with the state-of-the-art methods.
50
•Posted Content
Effects of Image Degradations to CNN-based Image Classification.
TL;DR: This paper empirically studies whether image-classification performance drops with each kind of degradation, whether this drop can be avoided by including degraded images into training, and whether existing computer vision algorithms that attempt to remove such degradations can help improve the image- classification performance.
22