The re-identification (ReID) task has received increasing studies in recent years and its performance has gained significant improvement. The progress mainly comes from searching for new network structures to learn person representations. However, limited efforts have been made to explore the potential performance of existing ReID networks directly by better training scheme, which leaves a large space for ReID research. In this paper, we propose a Self-Inspirited Feature Learning (SIF) method to enhance the performance of given ReID networks from the viewpoint of optimization. We design a simple adversarial learning scheme to encourage a network to learn more discriminative person representation. In our method, an auxiliary branch is added into the network only in the training stage, while the structure of the original network stays unchanged during the testing stage. In summary, SIF has three aspects of advantages: 1) it is designed under general setting; 2) it is compatible with many existing feature learning networks on the ReID task; 3) it is easy to implement and has steady performance. We evaluate the performance of SIF on three public ReID datasets: Market1501, DuckMTMC-reID, and CUHK03(both labeled and detected). The results demonstrate significant improvement in performance brought by SIF. We also apply SIF to obtain state-of-the-art results on all the three datasets. Specifically, mAP / Rank-1 accuracy are: 87.6%/95.2% (without re-rank) on Market1501, 79.4%/89.8% on DuckMTMC-reID, 77.0%/79.5% on CUHK03 (labeled) and 73.9%/76.6% on CUHK03 (detected), respectively.

中文翻译：

---

SIF：用于人员重新识别的自我启发特征学习


近年来，重新识别（ReID）任务得到了越来越多的研究，其性能得到了显着的提高。进展主要来自寻找新的网络结构来学习人物表示。然而，通过更好的训练方案直接探索现有ReID网络的潜在性能的努力有限，这为ReID研究留下了很大的空间。在本文中，我们提出了一种自启发特征学习（SIF）方法，从优化的角度增强给定 ReID 网络的性能。我们设计了一个简单的对抗性学习方案，以鼓励网络学习更具辨别力的人物表示。在我们的方法中，仅在训练阶段将辅助分支添加到网络中，而在测试阶段原始网络的结构保持不变。综上所述，SIF具有三个方面的优点：1）在通用环境下设计； 2）与ReID任务上的许多现有特征学习网络兼容； 3）易于实现，性能稳定。我们评估了 SIF 在三个公共 ReID 数据集上的性能：Market1501、DuckMTMC-reID 和 CUHK03（均已标记和检测）。结果表明 SIF 带来的性能显着提升。我们还应用 SIF 在所有三个数据集上获得最先进的结果。具体来说，mAP / Rank-1 准确度为：Market1501 上的 87.6%/95.2%（无需重新排名）、DuckMTMC-reID 上的 79.4%/89.8%、CUHK03 上的 77.0%/79.5%（已标记）和 73.9%/76.6%分别在 CUHK03（检测到）上。