Scale variation is one of the key challenges in object detection. In this work, we first present a controlled experiment to investigate the effect of receptive fields for scale variation in object detection. Based on the findings from the exploration experiments, we propose a novel Trident Network (TridentNet) aiming to generate scale-specific feature maps with a uniform representational power. We construct a parallel multi-branch architecture in which each branch shares the same transformation parameters but with different receptive fields. Then, we adopt a scale-aware training scheme to specialize each branch by sampling object instances of proper scales for training. As a bonus, a fast approximation version of TridentNet could achieve significant improvements without any additional parameters and computational cost compared with the vanilla detector. On the COCO dataset, our TridentNet with ResNet-101 backbone achieves state-of-the-art single-model results of 48.4 mAP. Codes are available at https://git.io/fj5vR.
翻译:比例变异是物体探测方面的主要挑战之一。 在这项工作中, 我们首先提出一个受控实验, 以调查物体探测中可接受范围变异域的影响。 根据探索实验的结果, 我们提出一个新的三叉戟网络( Trisid Net ), 旨在生成具有统一代表力的尺度特有地图。 我们建立一个平行的多部门结构, 每个分支共享相同的变异参数, 但拥有不同的可接受域 。 然后, 我们通过一个规模认知培训计划, 通过对适当规模的物体进行取样, 使每个分支专业化。 作为奖励, 三叉戟网络的快速近似版本可以在不增加参数和计算成本的情况下与香草探测器取得显著的改进。 在 COCO数据集中, 我们的三叉式网络, ResNet- 101 脊柱骨实现了48.4 mAP 的一模结果。 代码可在 https://git.io/ fj5vR 上查阅。