Learning latent features with local channel drop network for vehicle re-identification

Abstract

Vehicle re-identification targets to find the target vehicle images in a large dataset which is composed of vehicle images from multiple non-overlapping cameras. Due to the various illumination, viewpoints and resolutions, it is challenging to find the right vehicle images accurately. Most existing works put emphasis on learning strong features by exploiting the attention parts in vehicle images, which leads to some small important cues being suppressed by these significant parts. Hence, a local channel drop network (LCDNet) is proposed in this paper, which focuses on seeking the latent features by releasing the constraint of most attentive features. Specially, besides the normal local feature learning network, LCDNet consists of an attentive local feature learning branch that drops some regions to promote learning the attentive features of local regions. Besides, the batch ranking loss is introduced to split the samples into two groups in a batch and regularize them by enforcing a margin, which ensures the model to learn meaningful features to distinct vehicles. Moreover, to further calculate the similarity of various images, the paper proposes a multi-distance based ranking method to achieve more accurate results. Experiments on several benchmark datasets validate the effectiveness of the proposed method.