论文标题
重新识别的人的多样性调整慢电路网络
Diversity-Achieving Slow-DropBlock Network for Person Re-Identification
论文作者
论文摘要
使用多分支网络架构的人重新识别（RE-ID）的重大挑战是从ID标记的数据集中学习各种功能。最近提出了2个分支批处理底座（BDB）网络，以实现全球分支与特征引人入胜的分支之间的多样性。在本文中，我们建议将掉落操作从中间特征层移动到输入（图像删除）。由于它可能会丢弃大部分输入图像，因此这使训练难以收敛。因此，我们提出了一种新型的双批量分解共同训练方法来解决这个问题。特别是，我们表明，通过为每个分支设置单个掉落比例，可以通过使用多个掉落分支来实现特征多样性。经验证据表明，所提出的方法在流行人士重新ID数据集上的表现优于BDB，包括Market-1501，Dukemtmc-Reid和Cuhk03，并且使用更多的丢弃分支可以进一步提高性能。
A big challenge of person re-identification (Re-ID) using a multi-branch network architecture is to learn diverse features from the ID-labeled dataset. The 2-branch Batch DropBlock (BDB) network was recently proposed for achieving diversity between the global branch and the feature-dropping branch. In this paper, we propose to move the dropping operation from the intermediate feature layer towards the input (image dropping). Since it may drop a large portion of input images, this makes the training hard to converge. Hence, we propose a novel double-batch-split co-training approach for remedying this problem. In particular, we show that the feature diversity can be well achieved with the use of multiple dropping branches by setting individual dropping ratio for each branch. Empirical evidence demonstrates that the proposed method performs superior to BDB on popular person Re-ID datasets, including Market-1501, DukeMTMC-reID and CUHK03 and the use of more dropping branches can further boost the performance.
