In this paper, we propose a novel person Re-ID model, Consecutive Batch DropBlock Network (CBDB-Net), to capture the attentive and robust person descriptor for the person Re-ID task. The CBDB-Net contains two novel designs: the Consecutive Batch DropBlock Module (CBDBM) and the Elastic Loss (EL). In the Consecutive Batch DropBlock Module (CBDBM), we firstly conduct uniform partition on the feature maps. And then, we independently and continuously drop each patch from top to bottom on the feature maps, which can output multiple incomplete feature maps. In the training stage, these multiple incomplete features can better encourage the Re-ID model to capture the robust person descriptor for the Re-ID task. In the Elastic Loss (EL), we design a novel weight control item to help the Re-ID model adaptively balance hard sample pairs and easy sample pairs in the whole training process. Through an extensive set of ablation studies, we verify that the Consecutive Batch DropBlock Module (CBDBM) and the Elastic Loss (EL) each contribute to the performance boosts of CBDB-Net. We demonstrate that our CBDB-Net can achieve the competitive performance on the three standard person Re-ID datasets (the Market-1501, the DukeMTMC-Re-ID, and the CUHK03 dataset), three occluded Person Re-ID datasets (the Occluded DukeMTMC, the Partial-REID, and the Partial iLIDS dataset), and a general image retrieval dataset (In-Shop Clothes Retrieval dataset).
翻译:在本文中,我们提出一个新的人重新识别模型,即CBBB-Net,以捕捉对人再识别任务的关注和强健的人描述符。CBB-Net包含两个新的设计:C contrationive Bass DroppBlock模块(CBBM)和Elastial Loss(EL)。在Contatition Batch BroppBlock模块(CBBM)中,我们首先在地貌地图上进行统一的分隔。然后,我们在地貌地图上从上到下独立不断地将每个补丁从上到下下降,这可以输出多个不完整的功能图。在培训阶段,这些多重不完备的功能可以更好地鼓励重新识别模型来捕捉重新识别任务的强健健的人描述符。在Evaltial Loss(EL)中,我们设计了一个新的重量控制项目,以帮助重新ID模型适应性地平衡在整个培训过程中的硬式样本和简易的样品配对。通过一套广泛的线性研究,我们核实了CBS-Block 图像模块模块(CBBBBBBM-IM-ID) 和EARDSDSDS-S-S-S-S-SD-S-S-SD-SD-S-SDD-SDDD-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-SD-SD-SDDD-S-SD-SD-SD-S-S-S-S-S-SDD-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-SDDARDDDDARDDDDDDDDDDDDD-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S