# DatUS^2: Data-driven Unsupervised Semantic Segmentation with Pre-trained Self-supervised Vision Transformer Source: [DatUS^2: Data-driven Unsupervised Semantic Segmentation with Pre-trained Self-supervised Vision Transformer]() Collection index: [llms.txt]() Data updated: 2026-01-04T03:58:05.656Z Authors: Sonal Kumar, Arijit Sur, Rashmi Dutta Baruah Published: 2024-01-23T14:53:32.000Z ## Abstract Successive proposals of several self-supervised training schemes continue to emerge, taking one step closer to developing a universal foundation model. In this process, the unsupervised downstream tasks are recognized as one of the evaluation methods to validate the quality of visual features learned with a self-supervised training scheme. However, unsupervised dense semantic segmentation has not been explored as a downstream task, which can utilize and evaluate the quality of semantic information introduced in patch-level feature representations during self-supervised training of a vision transformer. Therefore, this paper proposes a novel data-driven approach for unsupervised semantic segmentation (DatUS^2) as a downstream task. DatUS^2 generates semantically consistent and dense pseudo annotate segmentation masks for the unlabeled image dataset without using any visual-prior or synchronized data. We compare these pseudo-annotated segmentation masks with ground truth masks for evaluating recent self-supervised training schemes to learn shared semantic properties at the patch level and discriminative semantic properties at the segment level. Finally, we evaluate existing state-of-the-art self-supervised training schemes with our proposed downstream task, i.e., DatUS^2. Also, the best version of DatUS^2 outperforms the existing state-of-the-art method for the unsupervised dense semantic segmentation task with 15.02% MiOU and 21.47% Pixel accuracy on the SUIM dataset. It also achieves a competitive level of accuracy for a large-scale and complex dataset, i.e., the COCO dataset. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Unsupervised Semantic Segmentation on SUIM (val)](): Unsupervised Semantic Segmentation; SUIM Dataset (val); mIoU: 34.02. - [Unsupervised Semantic Segmentation on COCO (val)](): Unsupervised Semantic Segmentation; COCO (val); mIoU: 0.1597. ## Original sources and implementation [Original paper]() [PDF]()