Transformer-based supervised pre-training achieves great performance in person re-identification (ReID). However, due to the domain gap between ImageNet and ReID datasets, it usually needs a larger pre-training dataset (e.g. ImageNet-21K) to boost the performance because of the strong data fitting ability of the transformer. To address this challenge, this work targets to mitigate the gap between the pre-training and ReID datasets from the perspective of data and model structure, respectively. We first investigate self-supervised learning (SSL) methods with Vision Transformer (ViT) pretrained on unlabelled person images (the LUPerson dataset), and empirically find it significantly surpasses ImageNet supervised pre-training models on ReID tasks. To further reduce the domain gap and accelerate the pre-training, the Catastrophic Forgetting Score (CFS) is proposed to evaluate the gap between pre-training and fine-tuning data. Based on CFS, a subset is selected via sampling relevant data close to the down-stream ReID data and filtering irrelevant data from the pre-training dataset. For the model structure, a ReID-specific module named IBN-based convolution stem (ICS) is proposed to bridge the domain gap by learning more invariant features. Extensive experiments have been conducted to fine-tune the pre-training models under supervised learning, unsupervised domain adaptation (UDA), and unsupervised learning (USL) settings. We successfully downscale the LUPerson dataset to 50% with no performance degradation. Finally, we achieve state-of-the-art performance on Market-1501 and MSMT17. For example, our ViT-S/16 achieves 91.3%/89.9%/89.6% mAP accuracy on Market1501 for supervised/UDA/USL ReID. Codes and models will be released to https://github.com/michuanhaohao/TransReID-SSL.
翻译:以变压器为基础的变压器前训练在个人再识别(ReID)方面表现良好。然而,由于图像网络和ReID数据集之间存在域差,通常需要更大的培训前数据集(例如图像Net-21K),以便通过变压器强大的数据适应能力提高性能。为了应对这一挑战,我们从数据和模型结构的角度出发,为缩小培训前和ReID数据集之间的差距而设定了这项工作目标。我们首先调查了自我监督的学习方法(SSLL),在未贴标签的人图像(LUPERS数据集)上预先训练了VIV.90(VT),在经验上发现它大大超过REID任务的培训前模型(例如图像Net-21KK)。为了进一步缩小域间隙,加速培训前训练,提议将Catasriftical 遗忘评分(CFS)从数据和调整前和调整数据。根据CFSFIS,通过取样相关数据接近下流流数据,将FIID数据筛选为S-ILD数据过滤不相关的数据,在IM-ILA 数据库前的升级模型中,我们正在开始的升级的模型-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-I-I-ID-ID-ID-I-I-I-I-I-I-I-ID-I-I-I-I-ID-ID-ID-ID-ID-ID-ID-ID-ID-ID-I-I-ID-I-I-I-I-I-ID-I-I-I-I-ID-I-I-I-I-I-I-I-I-I-I-I-I