In this paper, we describe a graph-based algorithm that uses the features obtained by a self-supervised transformer to detect and segment salient objects in images and videos. With this approach, the image patches that compose an image or video are organised into a fully connected graph, where the edge between each pair of patches is labeled with a similarity score between patches using features learned by the transformer. Detection and segmentation of salient objects is then formulated as a graph-cut problem and solved using the classical Normalized Cut algorithm. Despite the simplicity of this approach, it achieves state-of-the-art results on several common image and video detection and segmentation tasks. For unsupervised object discovery, this approach outperforms the competing approaches by a margin of 6.1%, 5.7%, and 2.6%, respectively, when tested with the VOC07, VOC12, and COCO20K datasets. For the unsupervised saliency detection task in images, this method improves the score for Intersection over Union (IoU) by 4.4%, 5.6% and 5.2%. When tested with the ECSSD, DUTS, and DUT-OMRON datasets, respectively, compared to current state-of-the-art techniques. This method also achieves competitive results for unsupervised video object segmentation tasks with the DAVIS, SegTV2, and FBMS datasets.

翻译：本文提出一种基于图的算法，利用自监督Transformer提取的特征对图像与视频中的显著性物体进行检测与分割。该方法将构成图像或视频的图像块组织为全连接图，其中每对图像块之间的边采用Transformer学习到的特征标注相似度分数。继而将显著性物体的检测与分割建模为图割问题，采用经典的归一化割算法求解。尽管方法简洁，但在多个常见图像与视频检测及分割任务中取得了当前最优结果。在无监督物体发现任务中，该方法在VOC07、VOC12和COCO20K数据集上分别以6.1%、5.7%和2.6%的优势超越现有方法。在图像无监督显著性检测任务中，该方法在ECSSD、DUTS和DUT-OMRON数据集上分别将交并比（IoU）指标提升了4.4%、5.6%和5.2%。在视频无监督物体分割任务中，该方法在DAVIS、SegTV2和FBMS数据集上同样取得了具有竞争力的结果。