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.
翻译:未经监督的物体发现(UOD)近来在采用经过预先训练的变异器特征方面取得了令人鼓舞的进展,然而,目前基于变异器的方法主要侧重于设计本地化头部(例如种子选择扩展和归正切割),忽视了改进变异器特征的重要性。在这项工作中,我们从特性增强的角度处理UOD任务,并提议了外观导和Multi-Layer特性融合,以进行未经监督的物体发现,称为FORMULA。首先,我们提出了一个带有现成的紫外UOD探测器的地表指导战略,以便在地貌图上突出地表区域,然后以迭接方式改进对象位置。此外,为了解决物体探测中的天体变化问题,我们设计了一个多层特性融合模块,以不同尺度对物体作出反应。关于VOC07、VOC12和COCOCO 20k的实验显示,拟议的FOMLA在未经监督的物体发现方面将取得新的状态-艺术结果。代码将在 https://GILUV. 发布于 AM/MUV.