In the paradigm of object detection, the decision head is an important part, which affects detection performance significantly. Yet how to design a high-performance decision head remains to be an open issue. In this paper, we propose a novel approach to combine decision trees and deep neural networks in an end-to-end learning manner for object detection. First, we disentangle the decision choices and prediction values by plugging soft decision trees into neural networks. To facilitate effective learning, we propose randomized decision routing with node selective and associative losses, which can boost the feature representative learning and network decision simultaneously. Second, we develop the decision head for object detection with narrow branches to generate the routing probabilities and masks, for the purpose of obtaining divergent decisions from different nodes. We name this approach as the randomized decision routing for object detection, abbreviated as R(Det)$^2$. Experiments on MS-COCO dataset demonstrate that R(Det)$^2$ is effective to improve the detection performance. Equipped with existing detectors, it achieves $1.4\sim 3.6$\% AP improvement.

本文提出了一种基于决策树和深度神经网络的端到端学习方法，用于改进物体检测的决策头问题，通过使用软决策树来拆分决策选择和预测值，并引入加权策略和关联损失实现了有效的学习，同时还使用狭窄的分支来生成路由概率和掩码，从不同节点获得不同的决策，并在 MS-COCO 数据集上的实验验证了其有效性。

R(Det)^2：面向物体检测的随机决策路由