Wasserstein Loss-Based Deep Object Detection

Object detection locates the objects with bounding boxes and identifies their classes, which is valuable in many computer vision applications (e.g. autonomous driving). Most existing deep learning-based methods output a probability vector for instance classification trained with the one-hot label. However, the limitation of these models lies in attribute perception because they do not take the severity of different misclassifications into consideration. In this paper, we propose a novel method based on the Wasserstein distance called Wasserstein Loss based Model for Object Detection (WLOD). Different from the commonly used distance metric such as cross-entropy (CE), the Wasserstein loss assigns different weights for one sample identified to different classes with different values. Our distance metric is designed by combining the CE or binary cross-entropy (BCE) with Wasserstein distance to learn the detector considering both the discrimination and the seriousness of different misclassifications. The misclassified objects are identified to similar classes with a higher probability to reduce intolerable misclassifications. Finally, the model is tested on the BDD100K and KITTI datasets and reaches state-of-the-art performance.