论文标题
前景指导和多层特征融合，用于无监督的对象发现变压器
Foreground Guidance and Multi-Layer Feature Fusion for Unsupervised Object Discovery with Transformers
论文作者
论文摘要
无监督的对象发现（UOD）最近通过采用预训练的变压器功能表明了令人鼓舞的进步。但是，基于变压器的当前方法主要集中于设计定位头（例如种子选择扩张和归一化切割），并忽略了改善变压器特征的重要性。在这项工作中，我们从功能增强的角度处理UOD任务，并提出了前景指导和多层功能融合，以供无监督的对象发现（称为配方）。首先，我们提出了一个前景指导策略，该策略采用现成的UOD探测器，以突出特征图上的前景区域，然后以迭代方式完善对象位置。此外，为了解决对象检测中的比例变化问题，我们设计了一个多层特征融合模块，该模块汇总了在不同尺度下响应对象的特征。 VOC07，VOC12和可可20K上的实验表明，所提出的公式可实现无监督的对象发现的最新最新结果。该代码将在https://github.com/vdigpku/formula上发布。
Unsupervised object discovery (UOD) has recently shown encouraging progress with the adoption of pre-trained Transformer features. However, current methods based on Transformers mainly focus on designing the localization head (e.g., seed selection-expansion and normalized cut) and overlook the importance of improving Transformer features. In this work, we handle UOD task from the perspective of feature enhancement and propose FOReground guidance and MUlti-LAyer feature fusion for unsupervised object discovery, dubbed FORMULA. Firstly, we present a foreground guidance strategy with an off-the-shelf UOD detector to highlight the foreground regions on the feature maps and then refine object locations in an iterative fashion. Moreover, to solve the scale variation issues in object detection, we design a multi-layer feature fusion module that aggregates features responding to objects at different scales. The experiments on VOC07, VOC12, and COCO 20k show that the proposed FORMULA achieves new state-of-the-art results on unsupervised object discovery. The code will be released at https://github.com/VDIGPKU/FORMULA.
