Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion

• URL: http://arxiv.org/abs/2308.12469v3
• Date: Tue, 2 Apr 2024 17:40:03 GMT
• Title: Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion
• Authors: Junjiao Tian, Lavisha Aggarwal, Andrea Colaco, Zsolt Kira, Mar Gonzalez-Franco,
• Abstract summary: We propose a model capable of segmenting anything in a zero-shot manner without any annotations. We introduce a simple yet effective iterative merging process based on measuring KL divergence among attention maps to merge them into valid segmentation masks. On COCO-Stuff-27, our method surpasses the prior unsupervised zero-shot SOTA method by an absolute 26% in pixel accuracy and 17% in mean IoU.
• Score: 24.02235805999193
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Producing quality segmentation masks for images is a fundamental problem in computer vision. Recent research has explored large-scale supervised training to enable zero-shot segmentation on virtually any image style and unsupervised training to enable segmentation without dense annotations. However, constructing a model capable of segmenting anything in a zero-shot manner without any annotations is still challenging. In this paper, we propose to utilize the self-attention layers in stable diffusion models to achieve this goal because the pre-trained stable diffusion model has learned inherent concepts of objects within its attention layers. Specifically, we introduce a simple yet effective iterative merging process based on measuring KL divergence among attention maps to merge them into valid segmentation masks. The proposed method does not require any training or language dependency to extract quality segmentation for any images. On COCO-Stuff-27, our method surpasses the prior unsupervised zero-shot SOTA method by an absolute 26% in pixel accuracy and 17% in mean IoU. The project page is at \url{https://sites.google.com/view/diffseg/home}.

Related papers

• UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation [64.01742988773745]
  An increasing privacy concern exists regarding training large-scale image segmentation models on unauthorized private data. We exploit the concept of unlearnable examples to make images unusable to model training by generating and adding unlearnable noise into the original images. We empirically verify the effectiveness of UnSeg across 6 mainstream image segmentation tasks, 10 widely used datasets, and 7 different network architectures.
  arXiv  Detail & Related papers  (2024-10-13T16:34:46Z)
• DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut [62.63481844384229]
  Foundation models have emerged as powerful tools across various domains including language, vision, and multimodal tasks. In this paper, we use a diffusion UNet encoder as a foundation vision encoder and introduce DiffCut, an unsupervised zero-shot segmentation method. Our work highlights the remarkably accurate semantic knowledge embedded within diffusion UNet encoders that could then serve as foundation vision encoders for downstream tasks.
  arXiv  Detail & Related papers  (2024-06-05T01:32:31Z)
• SOHES: Self-supervised Open-world Hierarchical Entity Segmentation [82.45303116125021]
  This work presents Self-supervised Open-world Hierarchical Entities (SOHES), a novel approach that eliminates the need for human annotations. We produce abundant high-quality pseudo-labels through visual feature clustering, and rectify the noises in pseudo-labels via a teacher- mutual-learning procedure. Using raw images as the sole training data, our method achieves unprecedented performance in self-supervised open-world segmentation.
  arXiv  Detail & Related papers  (2024-04-18T17:59:46Z)
• FreeSeg-Diff: Training-Free Open-Vocabulary Segmentation with Diffusion Models [56.71672127740099]
  We focus on the task of image segmentation, which is traditionally solved by training models on closed-vocabulary datasets. We leverage different and relatively small-sized, open-source foundation models for zero-shot open-vocabulary segmentation. Our approach (dubbed FreeSeg-Diff), which does not rely on any training, outperforms many training-based approaches on both Pascal VOC and COCO datasets.
  arXiv  Detail & Related papers  (2024-03-29T10:38:25Z)
• Unsupervised Universal Image Segmentation [59.0383635597103]
  We propose an Unsupervised Universal model (U2Seg) adept at performing various image segmentation tasks. U2Seg generates pseudo semantic labels for these segmentation tasks via leveraging self-supervised models. We then self-train the model on these pseudo semantic labels, yielding substantial performance gains.
  arXiv  Detail & Related papers  (2023-12-28T18:59:04Z)
• Exploring Open-Vocabulary Semantic Segmentation without Human Labels [76.15862573035565]
  We present ZeroSeg, a novel method that leverages the existing pretrained vision-language model (VL) to train semantic segmentation models. ZeroSeg overcomes this by distilling the visual concepts learned by VL models into a set of segment tokens, each summarizing a localized region of the target image. Our approach achieves state-of-the-art performance when compared to other zero-shot segmentation methods under the same training data.
  arXiv  Detail & Related papers  (2023-06-01T08:47:06Z)
• MaskSplit: Self-supervised Meta-learning for Few-shot Semantic Segmentation [10.809349710149533]
  We propose a self-supervised training approach for learning few-shot segmentation models. We first use unsupervised saliency estimation to obtain pseudo-masks on images. We then train a simple prototype based model over different splits of pseudo masks and augmentations of images.
  arXiv  Detail & Related papers  (2021-10-23T12:30:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.