Center Prediction Loss for Re-identification

Highlights：

• We propose a new intra-class loss called Center Prediction Loss (CPL). To the best of our knowledge, it is the first attempt to use the property of center predictivity as the loss function.

• We show that the CPL allows more freedom for choosing the intra-class distribution family and can naturally preserving the discrimination between samples from different classes.

• Extensive experiments on various ReID benchmarks show that the proposed loss can achieve superior performance and can also be complementary to existing losses. We also achieve new state-of-the-art performance on multiple ReID benchmarks.