Generate and Purify: Efficient Person Data Generation for Re-Identification

Generating person images has been a promising approach to enhance the input richness for re-identification (reID) tasks in recent works. A key challenge is that the generated data often contains noise, which is caused by identity inconsistency between the generated person and the original input and failure cases in generative adversarial networks (GAN). Directly training using generated images may greatly affect learning good feature embeddings, resulting in unsatisfactory reID performance. This work presents a two-stage framework that can generate high-quality person images and purify failure cases for reID training. Experimental results demonstrate that our proposed generative model can produce person images with superior appearance consistency comparing with other state-of-the-art methods. Furthermore, we show that our method yields a significant improvement in re-identification (reID) task on public datasets with insufficient training data.