2021 · 11 citations · 27 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine LearningDeep LearningGenerative ModelingImage Feature EngineeringRepresentation LearningSupervised LearningDisentangled Representation LearningImage Re-identificationPerson Re-identification
Despite the success of single-domain person re-identification (ReID), current supervised models degrade dramatically when deployed to unseen domains, mainly due to the discrepancy across cameras. To tackle this issue, we propose an Adversarial Disentangling Learning (ADL) framework to decouple camera-related and ID-related features, which can be readily used for camera-agnostic person ReID. ADL adopts a discriminative way instead of the mainstream generative styles in disentangling methods, eg., GAN or VAE based, because for person ReID task only the information to discriminate IDs is needed, and more information to generate images are redundant and may be noisy. Specifically, our model involves a feature separation module that encodes images into two separate feature spaces and a disentangled feature learning module that performs adversarial training to minimize mutual information. We design an effective solution to approximate and minimize mutual information by transforming it into a discrimination problem. The two modules are co-designed to obtain strong generalization ability by only using source dataset. Extensive experiments on three public benchmarks show that our method outperforms the state-of-the-art generalizable person ReID model by a large margin. Our code is publicly available at https://github.com/luckyaci/ADL_ReID.
27
Scalable Person Re-identification: A Benchmark
Liang Zheng, Liyue Shen, Lu Tian et al. · 2015 · 4.6K citations
Person Transfer GAN to Bridge Domain Gap for Person Re-identification
Longhui Wei, Shiliang Zhang, Wen Gao et al. · 2018 · 2K citations
Re-ranking Person Re-identification with k-Reciprocal Encoding
Zhun Zhong, Liang Zheng, Donglin Cao et al. · 2017 · 1.5K citations · Full text
Bag of Tricks and a Strong Baseline for Deep Person Re-Identification
Hao Luo, Youzhi Gu, Xingyu Liao et al. · 2019 · 1.5K citations