Enhance Visual Recognition Under Adverse Conditions via Deep Networks

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

Research output: Contribution to journalArticlepeer-review


Visual recognition under adverse conditions is a very important and challenging problem of high practical value, due to the ubiquitous existence of quality distortions during image acquisition, transmission, or storage. While deep neural networks have been extensively exploited in the techniques of low-quality image restoration and high-quality image recognition tasks, respectively, few studies have been done on the important problem of recognition from very low-quality images. This paper proposes a deep learning-based framework for improving the performance of image and video recognition models under adverse conditions, using robust adverse pre-training or its aggressive variant. The robust adverse pre-training algorithms leverage the power of pre-training and generalize the conventional unsupervised pre-training and data augmentation methods. We further develop a transfer learning approach to cope with real-world datasets of unknown adverse conditions. The proposed framework is comprehensively evaluated on a number of image and video recognition benchmarks, and obtains significant performance improvements under various single or mixed adverse conditions. Our visualization and analysis further add to the explainability of the results.

Original languageEnglish (US)
Article number8678738
Pages (from-to)4401-4412
Number of pages12
JournalIEEE Transactions on Image Processing
Issue number9
StatePublished - Sep 2019


  • Deep learning
  • image recognition
  • neural network

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'Enhance Visual Recognition Under Adverse Conditions via Deep Networks'. Together they form a unique fingerprint.

Cite this