“…Despite recent progress in vehicle reID, in particular deep learning models have made some progress [7], [8], [9], [10], it still suffers from lots of difficulties caused by various viewpoints of vehicles, complicated environments and diversified illuminations, which makes a great difference in the visual appearance of vehicles. Different from other vision tasks [11], [12] , such as person ReID [13], [14], [15], [16] and fine-grained [17], [18], [19], [20], that can extract rich features from images with various poses and colors, vehicles usually have a few attributes that could be utilized to help extract distinctive features for similar vehicles.…”