Existing methods enhance the training of detection transformers by incorporating an auxiliary one-to-many assignment. In this work, we treat the model as a multi-task framework, simultaneously performing one-to-one and one-to-many predictions. We investigate the roles of each component in the transformer decoder across these two training targets, including self-attention, cross-attention, and feed-forward network. Our empirical results demonstrate that any independent component in the decoder can effectively learn both targets simultaneously, even when other components are shared. This finding leads us to propose a multi-route training mechanism, featuring a primary route for one-to-one prediction and two auxiliary training routes for one-to-many prediction. We enhance the training mechanism with a novel instructive self-attention that dynamically and flexibly guides object queries for one-to-many prediction. The auxiliary routes are removed during inference, ensuring no impact on model architecture or inference cost. We conduct extensive experiments on various baselines, achieving consistent improvements as shown in Figure 1.

翻译：现有方法通过引入辅助的一对多分配来增强检测Transformer的训练。本文中，我们将模型视为一个多任务框架，同时执行一对一和一对多预测。我们研究了Transformer解码器中各组件在这两种训练目标下的作用，包括自注意力、交叉注意力和前馈网络。实验结果表明，即使其他组件共享，解码器中的任何独立组件都能有效同时学习这两种目标。这一发现促使我们提出一种多路径训练机制，包含一条用于一对一预测的主路径和两条用于一对多预测的辅助训练路径。我们通过一种新颖的指导性自注意力来增强该训练机制，该机制能动态灵活地引导对象查询进行一对多预测。辅助路径在推理阶段被移除，确保不影响模型架构或推理成本。我们在多种基线上进行了广泛实验，如图1所示，取得了持续的性能提升。