Visual Recognition in Very Low-Quality Settings: Delving into the Power of Pre-Training

Bowen Cheng, Ding Liu, Zhangyang Wang, Haichao Zhang, Thomas S. Huang

AAAI 2018 pp. 8065-8066

doi:10.1609/AAAI.V32I1.12131 /aaai/2018/cheng2018aaai-visual/

Abstract

Visual recognition from very low-quality images is an extremely challenging task with great practical values. While deep networks have been extensively applied to low-quality image restoration and high-quality image recognition tasks respectively, few works have been done on the important problem of recognition from very low-quality images.This paper presents a degradation-robust pre-training approach on improving deep learning models towards this direction. Extensive experiments on different datasets validate the effectiveness of our proposed method.

PDF AAAI Semantic Scholar

Cite

Text

Cheng et al. "Visual Recognition in Very Low-Quality Settings: Delving into the Power of Pre-Training." AAAI Conference on Artificial Intelligence, 2018. doi:10.1609/AAAI.V32I1.12131

Markdown

[Cheng et al. "Visual Recognition in Very Low-Quality Settings: Delving into the Power of Pre-Training." AAAI Conference on Artificial Intelligence, 2018.](https://mlanthology.org/aaai/2018/cheng2018aaai-visual/) doi:10.1609/AAAI.V32I1.12131

BibTeX

@inproceedings{cheng2018aaai-visual,
  title     = {{Visual Recognition in Very Low-Quality Settings: Delving into the Power of Pre-Training}},
  author    = {Cheng, Bowen and Liu, Ding and Wang, Zhangyang and Zhang, Haichao and Huang, Thomas S.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2018},
  pages     = {8065-8066},
  doi       = {10.1609/AAAI.V32I1.12131},
  url       = {https://mlanthology.org/aaai/2018/cheng2018aaai-visual/}
}