论文标题
重新识别的人的层次结构学习
Hierarchical and Efficient Learning for Person Re-Identification
论文作者
论文摘要
人重新识别任务的最新作品主要集中在模型准确性上，而忽略了与效率相关的因素，例如模型大小和潜伏期，这对于实际应用至关重要。在本文中，我们提出了一个新型的层次和高效网络（HENET），该网络（HENET）在多个损失组合的监督下学习层次的全球，部分和恢复功能合奏。为了进一步提高针对不规则闭塞的鲁棒性，我们提出了一种新的数据集增强方法，称为随机多边形擦除（RPE），以随机擦除输入图像的不规则面积，以模仿身体部位缺失。我们还提出了效率评分（ES）度量来评估模型效率。与时期制造方法相比，Market1501，Dukemtmc-Reid和Cuhk03数据集的广泛实验显示了我们方法的效率和优势。
Recent works in the person re-identification task mainly focus on the model accuracy while ignore factors related to the efficiency, e.g. model size and latency, which are critical for practical application. In this paper, we propose a novel Hierarchical and Efficient Network (HENet) that learns hierarchical global, partial, and recovery features ensemble under the supervision of multiple loss combinations. To further improve the robustness against the irregular occlusion, we propose a new dataset augmentation approach, dubbed Random Polygon Erasing (RPE), to random erase irregular area of the input image for imitating the body part missing. We also propose an Efficiency Score (ES) metric to evaluate the model efficiency. Extensive experiments on Market1501, DukeMTMC-ReID, and CUHK03 datasets shows the efficiency and superiority of our approach compared with epoch-making methods.
