Authors: Emir Mujić, Janez Perš, Darko Stern
Abstract: In this paper, we introduce a framework for evaluating style transfer methods that simulate desired target weather conditions from source images, acquired in fair weather. The resulting images can be used for targeted augmentation of datasets geared toward object detection. Our approach diverges from traditional measures that focus on human perception only, and importantly, does not rely on annotated datasets. Instead, we operate on statistical distribution of outcomes of the inference process (in our case, object detections).<br/><br/>The proposed evaluation measure effectively penalizes methods that preserve features and consistencies in object detection, and awards those, which generate challenging cases more similar to the target style. This is counteracted by the requirements that the generated images remain similar to the images acquired in target weather conditions.<br/><br/>This shift enables a more relevant and computationally practical assessment of style transfer techniques in the context of weather condition generation. By reducing the dependency on annotated datasets, our methodology offers a more streamlined and accessible approach to evaluation.
[PDF]