Wasserstein Loss based Deep Object Detection
Yuzhuo Han, Xiaofeng Liu, Zhenfei Sheng, Yutao Ren, Xu Han, Jane You, Risheng Liu, Zhongxuan Luo · 2020
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.