论文标题
封闭域不变的特征分离域可概括对象检测
Gated Domain-Invariant Feature Disentanglement for Domain Generalizable Object Detection
论文作者
论文摘要
对于域可推广的对象检测（DGOD），通过明确删除特定于域的表示（DSR）明确删除域 - 信号表示（DIR），可以通过明确删除域名表示（DIR）来实现很多帮助。考虑到域类别是输入数据的属性，网络应该适合特定的映射，该特定映射将DSR投影到特定于域特定信息的特定域中，因此可以简单地在通道维度上实现DSR的更清洁DSR。受这个想法的启发，我们提出了一种新颖的DGOD DGOD方法，该方法称为封闭域，不变特征分离（GDIFD）。在GDIFD中，通道门模块（CGM）学会了输出接近0或1的通道信号，该信号可以掩盖特定于域特定信息的通道对域识别有用。借助拟议的GDIFD，我们框架中的骨干可以轻松地拟合所需的映射，从而使频道的脱离构图。在实验中，我们证明我们的方法是非常有效的，并且可以实现最先进的DGOD性能。
For Domain Generalizable Object Detection (DGOD), Disentangled Representation Learning (DRL) helps a lot by explicitly disentangling Domain-Invariant Representations (DIR) from Domain-Specific Representations (DSR). Considering the domain category is an attribute of input data, it should be feasible for networks to fit a specific mapping which projects DSR into feature channels exclusive to domain-specific information, and thus much cleaner disentanglement of DIR from DSR can be achieved simply on channel dimension. Inspired by this idea, we propose a novel DRL method for DGOD, which is termed Gated Domain-Invariant Feature Disentanglement (GDIFD). In GDIFD, a Channel Gate Module (CGM) learns to output channel gate signals close to either 0 or 1, which can mask out the channels exclusive to domain-specific information helpful for domain recognition. With the proposed GDIFD, the backbone in our framework can fit the desired mapping easily, which enables the channel-wise disentanglement. In experiments, we demonstrate that our approach is highly effective and achieves state-of-the-art DGOD performance.
