Enhance Visual Recognition under Adverse Conditions via Deep Networks
This addresses the practical challenge of recognizing images or videos with distortions for applications in fields like surveillance or autonomous driving, but it is incremental as it builds on existing pre-training and data augmentation methods.
The paper tackles the problem of visual recognition from low-quality images under adverse conditions by proposing a deep learning framework using robust adverse pre-training and transfer learning, achieving significant performance improvements on multiple benchmarks.
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 generalizes 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 results.