Wei Long, Wei Zhenyong, Jin Zhongming, Yu Zhengxu, Huang Jianqiang, Cai Deng, He Xiaofei, Hua Xian-Sheng
IEEE Trans Image Process. 2020 Mar 4. doi: 10.1109/TIP.2020.2975712.
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. Most of these networks are trained using the classic stochastic gradient descent optimizer. However, limited efforts have been made to explore 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 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. The code of SIF will be available soon.
重新识别（ReID）任务近年来受到了越来越多的研究，其性能也有了显著提升。这一进展主要源于寻找新的网络结构来学习人物表征。这些网络大多使用经典的随机梯度下降优化器进行训练。然而，通过更好的训练方案直接探索现有ReID网络的潜在性能的工作还比较有限，这为ReID研究留下了很大的空间。在本文中，我们提出了一种自我激励特征学习（SIF）方法，从优化的角度提升给定ReID网络的性能。我们设计了一种简单的对抗学习方案，以鼓励网络学习更具判别力的人物表征。在我们的方法中，仅在训练阶段在网络中添加一个辅助分支，而在测试阶段原始网络的结构保持不变。总之，SIF具有三个方面的优势：（1）它是在一般设置下设计的；（2）它与ReID任务中的许多现有特征学习网络兼容；（3）它易于实现且性能稳定。我们在三个公开的ReID数据集上评估了SIF的性能：Market1501、DuckMTMC-reID和CUHK03（标记和检测版本）。结果表明SIF带来了性能上的显著提升。我们还将SIF应用于这三个数据集并取得了当前最优的结果。具体而言，在Market1501上，mAP / Rank-1准确率分别为87.6% / 95.2%（无重排序），在DuckMTMC-reID上为79.4% / 89.8%，在CUHK03（标记）上为77.0% / 79.5%，在CUHK03（检测）上为73.9% / 76.6%。SIF的代码即将发布。
