Cross-Domain Image Classification through Neural-Style Transfer Data Augmentation
This work addresses the challenge of domain adaptation for computer vision in specific adverse weather scenarios, but it is incremental as it applies an existing style-transfer method to a new dataset.
The paper tackled the problem of insufficient domain-specific data for image classification by using neural-style transfer data augmentation to improve automobile detection under adverse winter weather conditions, achieving improved accuracy on blizzard-condition images compared to classifiers trained only on normal images.
In particular, the lack of sufficient amounts of domain-specific data can reduce the accuracy of a classifier. In this paper, we explore the effects of style transfer-based data transformation on the accuracy of a convolutional neural network classifiers in the context of automobile detection under adverse winter weather conditions. The detection of automobiles under highly adverse weather conditions is a difficult task as such conditions present large amounts of noise in each image. The InceptionV2 architecture is trained on a composite dataset, consisting of either normal car image dataset , a mixture of normal and style transferred car images, or a mixture of normal car images and those taken at blizzard conditions, at a ratio of 80:20. All three classifiers are then tested on a dataset of car images taken at blizzard conditions and on vehicle-free snow landscape images. We evaluate and contrast the effectiveness of each classifier upon each dataset, and discuss the strengths and weaknesses of style-transfer based approaches to data augmentation.