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

Abstract

The main contribution of this paper is a simple semisupervised 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 .

Intra-Camera Supervised Person Re-Identification: A New Benchmark

“…Due to no existing re-id datasets for the proposed scenario, we introduced three ICS re-id benchmarks. We simulated the ICS identity annotation process on three existing large person re-id datasets, Market-1501 (Zheng et al, 2015), DukeMTMC-reID (Ristani et al, 2016;Zheng et al, 2017) and MSMT17 (Wei et al, 2018). Specifically, for the training data of each dataset, we independently perturbed the original identity labels for every individual camera view, and ensured that the same class labels of any pair of different camera views correspond to two unique persons (i.e.…”

Unsupervised Person Re-identification via Cross-Camera Similarity Exploration

“…The DukeMTMC-reID dataset [47] is a subset of the DukeMTMC dataset [22]. It contains 1812 identities captured by 8 cameras.…”

“…It contains 1812 identities captured by 8 cameras. Using the evaluation protocol specified in [47], we obtain 2228 query images, 16522 training images and 17661 gallery images.…”

An Empirical Study of Person Re-Identification with Attributes

“…Recently, supervised learning frameworks comprising of CNNs have been used for re-ID because of their ability to capture semantic and spatial information [8], [9], [21]- [23]. Broadly, the methods can be divided into two categories: deep representation learning and deep metric learning.…”