Distilled Person Re-Identification: Towards a More Scalable System

By Ancong Wu, Weishi Zheng, Xiaowei Guo, J. Lai. 2019

97 citations recorded by the source corpus.

Person re-identification (Re-ID), for matching pedestrians across non-overlapping camera views, has made great progress in supervised learning with abundant labelled data. However, the scalability problem is the bottleneck for applications in large-scale systems. We consider the scalability problem of Re-ID from three aspects: (1) low labelling cost by reducing label amount, (2) low extension cost by reusing existing knowledge and (3) low testing computation cost by using lightweight models. The requirements render scalable Re-ID a challenging problem. To solve these problems in a unified system, we propose a Multi-teacher Adaptive Similarity Distillation Framework, which requires only a few labelled identities of target domain to transfer knowledge from multiple teacher models to a user-specified lightweight student model without accessing source domain data. We propose the Log-Euclidean Similarity Distillation Loss for Re-ID and further integrate the Adaptive Knowledge Aggregator to select effective teacher models to transfer target-adaptive knowledge. Extensive evaluations show that our method can extend with high scalability and the performance is comparable to the state-of-the-art unsupervised and semi-supervised Re-ID methods.

Subfields: Computer Vision and Pattern Recognition, Efficiency & Compression

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Efficiency & Compression

Citations in the corpus

Ensemble Distillation for Robust Model Fusion in Federated Learning (2020, methodology): “In contrast, ensemble learning methods (You et al., 2017; Furlanello et al., 2018; Anil et al., 2018; Dvornik et al., 2019; Park & Kwak, 2019; Liu et al., 2019; Wu et al., 2019) allow to combine multiple heterogeneous weak classifiers by averaging the predictions of the individual models instead.”
Knowledge Distillation: A Survey (2020, background): “…mutual teacher–student networks (Thoker and Gall 2019), multiple stream networks (Garcia et al. 2018), spatiotemporal distilled dense-connectivity network (Hao and Zhang 2019), graph distillation (Luo et al. 2018) and multi-teacher to multi-student networks (Wu et al. 2019b; Zhang et al. 2020c).”
Universal Source-Free Domain Adaptation (2020, background): “Moreover, in real-time deployment scenarios [51], training on the entire source data is not feasible due to computational limitations.”
Deep Learning for Person Re-Identification: A Survey and Outlook (2020, background): “, a multi-teacher adaptive similarity distillation framework is proposed in [239], which learns a user-specified lightweight student model from multiple teacher models, without access to source domain data.”
Complementary Relation Contrastive Distillation (2021, background): “Knowledge distillation aims to transfer the knowledge from one deep learning model (the teacher) to another (the student), such as distilling a large network into a smaller one [19, 49, 2, 48, 12] or ensembling a collection of models into a single model [29, 37, 27, 45].”
A Comprehensive Survey on Test-Time Adaptation Under Distribution Shifts (2023, unknown): “, person re-identification [457], [582] and sketch-to-image retrieval [433], [445].”