# Rethinking Person Re-Identification via Semantic-Based Pretraining Source: [Rethinking Person Re-Identification via Semantic-Based Pretraining]() Collection index: [llms.txt]() Data updated: 2025-10-26T00:54:03.791Z Authors: Suncheng Xiang, Jingsheng Gao, Zirui Zhang, Mengyuan Guan, Binjie Yan, Ting Liu, Dahong Qian, Yuzhuo Fu Published: 2021-10-11T08:19:45.000Z ## Abstract Pretraining is a dominant paradigm in computer vision. Generally, supervised ImageNet pretraining is commonly used to initialize the backbones of person re-identification (Re-ID) models. However, recent works show a surprising result that CNN-based pretraining on ImageNet has limited impacts on Re-ID system due to the large domain gap between ImageNet and person Re-ID data. To seek an alternative to traditional pretraining, here we investigate semantic-based pretraining as another method to utilize additional textual data against ImageNet pretraining. Specifically, we manually construct a diversified FineGPR-C caption dataset for the first time on person Re-ID events. Based on it, a pure semantic-based pretraining approach named VTBR is proposed to adopt dense captions to learn visual representations with fewer images. We train convolutional neural networks from scratch on the captions of FineGPR-C dataset, and then transfer them to downstream Re-ID tasks. Comprehensive experiments conducted on benchmark datasets show that our VTBR can achieve competitive performance compared with ImageNet pretraining - despite using up to 1.4x fewer images, revealing its potential in Re-ID pretraining. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()