On Classification of Distorted Images with Deep Convolutional Neural Networks
This addresses the issue of robust image classification for applications in computer vision, but it is incremental as it builds on existing methods.
The paper tackled the problem of image distortions like blur and noise affecting deep neural network classifiers, finding that fine-tuning with noisy images can significantly alleviate these effects under certain conditions and is more practical than retraining.
Image blur and image noise are common distortions during image acquisition. In this paper, we systematically study the effect of image distortions on the deep neural network (DNN) image classifiers. First, we examine the DNN classifier performance under four types of distortions. Second, we propose two approaches to alleviate the effect of image distortion: re-training and fine-tuning with noisy images. Our results suggest that, under certain conditions, fine-tuning with noisy images can alleviate much effect due to distorted inputs, and is more practical than re-training.