Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro

ICCV 2017  ·  Zhedong Zheng, Liang Zheng, Yi Yang ·

The main contribution of this paper is a simple semi-supervised pipeline that only uses the original training set without collecting extra data. It is challenging in 1) how to obtain more training data only from the training set and 2) how to use the newly generated data. In this work, the generative adversarial network (GAN) is used to generate unlabeled samples. We propose the label smoothing regularization for outliers (LSRO). This method assigns a uniform label distribution to the unlabeled images, which regularizes the supervised model and improves the baseline. We verify the proposed method on a practical problem: person re-identification (re-ID). This task aims to retrieve a query person from other cameras. We adopt the deep convolutional generative adversarial network (DCGAN) for sample generation, and a baseline convolutional neural network (CNN) for representation learning. Experiments show that adding the GAN-generated data effectively improves the discriminative ability of learned CNN embeddings. On three large-scale datasets, Market-1501, CUHK03 and DukeMTMC-reID, we obtain +4.37%, +1.6% and +2.46% improvement in rank-1 precision over the baseline CNN, respectively. We additionally apply the proposed method to fine-grained bird recognition and achieve a +0.6% improvement over a strong baseline. The code is available at https://github.com/layumi/Person-reID_GAN.

PDF Abstract ICCV 2017 PDF ICCV 2017 Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Fine-Grained Image Classification CUB-200-2011 Basel.+LSRO Accuracy 84.4 # 23
Person Re-Identification CUHK03 VI+LSRO 3 MAP 87.4 # 4
Rank-1 84.6 # 7
Person Re-Identification DukeMTMC-reID GAN Rank-1 67.68 # 77
mAP 47.13 # 82
Person Re-Identification Market-1501 GAN Rank-1 83.97 # 96
mAP 66.07 # 101


No methods listed for this paper. Add relevant methods here