论文标题
自适应L2正则重新识别
Adaptive L2 Regularization in Person Re-Identification
论文作者
论文摘要
我们在人重新识别的情况下引入了一种自适应L2正则化机制。在文献中，使用手工挑选的正则化因子是在整个训练过程中保持恒定的常见实践。与现有方法不同，我们提出的方法中的正则化因素是通过反向传播自适应更新的。这是通过将可训练的标量变量纳入正则化因子来实现的，该因子将进一步馈送到缩放的硬乙状体功能中。市场1501，DUKEMTMC-REID和MSMT17数据集进行了广泛的实验验证了我们框架的有效性。最值得注意的是，我们在MSMT17上获得最先进的性能，这是人重新识别的最大数据集。源代码可在https://github.com/nixingyang/adaptivel2regularization上公开获取。
We introduce an adaptive L2 regularization mechanism in the setting of person re-identification. In the literature, it is common practice to utilize hand-picked regularization factors which remain constant throughout the training procedure. Unlike existing approaches, the regularization factors in our proposed method are updated adaptively through backpropagation. This is achieved by incorporating trainable scalar variables as the regularization factors, which are further fed into a scaled hard sigmoid function. Extensive experiments on the Market-1501, DukeMTMC-reID and MSMT17 datasets validate the effectiveness of our framework. Most notably, we obtain state-of-the-art performance on MSMT17, which is the largest dataset for person re-identification. Source code is publicly available at https://github.com/nixingyang/AdaptiveL2Regularization.
