Fully convolutional detectors discard the one-to-many assignment and adopt a one-to-one assigning strategy to achieve end-to-end detection but suffer from the slow convergence issue. In this paper, we revisit these two assignment methods and find that bringing one-to-many assignment back to end-to-end fully convolutional detectors helps with model convergence. Based on this observation, we propose {\em \textbf{D}ual \textbf{A}ssignment} for end-to-end fully convolutional de\textbf{TE}ction (DATE). Our method constructs two branches with one-to-many and one-to-one assignment during training and speeds up the convergence of the one-to-one assignment branch by providing more supervision signals. DATE only uses the branch with the one-to-one matching strategy for model inference, which doesn't bring inference overhead. Experimental results show that Dual Assignment gives nontrivial improvements and speeds up model convergence upon OneNet and DeFCN. Code: https://github.com/YiqunChen1999/date.
翻译:完全进化探测器丢弃一到多项任务, 并采取一到一分配策略实现端到端的检测, 但却受到缓慢的趋同问题的影响。 在本文件中, 我们重新审视了这两种任务方法, 发现将一到多项任务带回端到端到端完全进化探测器有助于模型的趋同。 基于此观察, 我们提议为端到端完全进端的全进化调, 并采取一到一分配策略, 实现端到端的检测, 但受到缓慢的趋同问题 。 我们的方法在培训期间用一到Man和一对一任务构建了两个分支, 并通过提供更多的监督信号加快一到一任务分支的趋同。 DATE只使用一到一匹配的模型推论战略, 这不会带来推断性管理。 实验结果显示, 双重分配给Onet 和 DeFCN 代码 : https://github.com/Yqun C 带来非全局性改进, 并加速模型的趋同 。 https://github.