Consistency-Preserving deep hashing for fast person re-identification

Highlights：

• We design a new hash structure to guide the hash code learning to be consistent with the high-dimensional feature learning by applying the same softmax classification loss and an improved triplet distance metric learning loss respectively.

• We propose an effective noise consistency loss to optimize high-dimensional feature learning and hash code extraction in a more robust direction, to keep the prediction of two models same. And these two models are provided with the same image with different noises.

• We propose a new implementation of topology constraint, which bridge the gap caused by feature binarization, and preserve the topology consistency with ordinal relation and label information.

• Comprehensive experimental results on the three widely used datasets with various experimental settings demonstrate the superiority of our proposed method.