InvSeg: Test-Time Prompt Inversion for Semantic Segmentation

• URL: http://arxiv.org/abs/2410.11473v2
• Date: Fri, 03 Jan 2025 18:59:28 GMT
• Title: InvSeg: Test-Time Prompt Inversion for Semantic Segmentation
• Authors: Jiayi Lin, Jiabo Huang, Jian Hu, Shaogang Gong,
• Abstract summary: InvSeg is a test-time prompt inversion method that tackles open-vocabulary semantic segmentation. We introduce Contrastive Soft Clustering (CSC) to align derived masks with the image's structure information. InvSeg learns context-rich text prompts in embedding space and achieves accurate semantic alignment across modalities.
• Score: 33.60580908728705
• License:
• Abstract: Visual-textual correlations in the attention maps derived from text-to-image diffusion models are proven beneficial to dense visual prediction tasks, e.g., semantic segmentation. However, a significant challenge arises due to the input distributional discrepancy between the context-rich sentences used for image generation and the isolated class names typically used in semantic segmentation. This discrepancy hinders diffusion models from capturing accurate visual-textual correlations. To solve this, we propose InvSeg, a test-time prompt inversion method that tackles open-vocabulary semantic segmentation by inverting image-specific visual context into text prompt embedding space, leveraging structure information derived from the diffusion model's reconstruction process to enrich text prompts so as to associate each class with a structure-consistent mask. Specifically, we introduce Contrastive Soft Clustering (CSC) to align derived masks with the image's structure information, softly selecting anchors for each class and calculating weighted distances to push inner-class pixels closer while separating inter-class pixels, thereby ensuring mask distinction and internal consistency. By incorporating sample-specific context, InvSeg learns context-rich text prompts in embedding space and achieves accurate semantic alignment across modalities. Experiments show that InvSeg achieves state-of-the-art performance on the PASCAL VOC, PASCAL Context and COCO Object datasets.

Related papers

• Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation [28.24883865053459]
  This paper aims to learn a model capable of segmenting arbitrary visual concepts within images by using only image-text pairs without dense annotations. Existing methods have demonstrated that contrastive learning on image-text pairs effectively aligns visual segments with the meanings of texts. A text often consists of multiple semantic concepts, whereas semantic segmentation strives to create semantically homogeneous segments.
  arXiv  Detail & Related papers  (2024-04-05T17:25:17Z)
• Semantic Prompt Learning for Weakly-Supervised Semantic Segmentation [33.336549577936196]
  Weakly-Supervised Semantic (WSSS) aims to train segmentation models using image data with only image-level supervision. We propose a Semantic Prompt Learning for WSSS (SemPLeS) framework, which learns to effectively prompt the CLIP latent space. SemPLeS can perform better semantic alignment between object regions and class labels, resulting in desired pseudo masks for training segmentation models.
  arXiv  Detail & Related papers  (2024-01-22T09:41:05Z)
• Leveraging Open-Vocabulary Diffusion to Camouflaged Instance Segmentation [59.78520153338878]
  Text-to-image diffusion techniques have shown exceptional capability of producing high-quality images from text descriptions. We propose a method built upon a state-of-the-art diffusion model, empowered by open-vocabulary to learn multi-scale textual-visual features for camouflaged object representations.
  arXiv  Detail & Related papers  (2023-12-29T07:59:07Z)
• FuseNet: Self-Supervised Dual-Path Network for Medical Image Segmentation [3.485615723221064]
  FuseNet is a dual-stream framework for self-supervised semantic segmentation. Cross-modal fusion technique extends the principles of CLIP by replacing textual data with augmented images. experiments on skin lesion and lung segmentation datasets demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2023-11-22T00:03:16Z)
• Text Augmented Spatial-aware Zero-shot Referring Image Segmentation [60.84423786769453]
  We introduce a Text Augmented Spatial-aware (TAS) zero-shot referring image segmentation framework. TAS incorporates a mask proposal network for instance-level mask extraction, a text-augmented visual-text matching score for mining the image-text correlation, and a spatial for mask post-processing. The proposed method clearly outperforms state-of-the-art zero-shot referring image segmentation methods.
  arXiv  Detail & Related papers  (2023-10-27T10:52:50Z)
• Zero-shot spatial layout conditioning for text-to-image diffusion models [52.24744018240424]
  Large-scale text-to-image diffusion models have significantly improved the state of the art in generative image modelling. We consider image generation from text associated with segments on the image canvas, which combines an intuitive natural language interface with precise spatial control over the generated content. We propose ZestGuide, a zero-shot segmentation guidance approach that can be plugged into pre-trained text-to-image diffusion models.
  arXiv  Detail & Related papers  (2023-06-23T19:24:48Z)
• ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency [126.88107868670767]
  We propose multi-textbfView textbfConsistent learning (ViewCo) for text-supervised semantic segmentation. We first propose text-to-views consistency modeling to learn correspondence for multiple views of the same input image. We also propose cross-view segmentation consistency modeling to address the ambiguity issue of text supervision.
  arXiv  Detail & Related papers  (2023-01-31T01:57:52Z)
• Language-driven Semantic Segmentation [88.21498323896475]
  We present LSeg, a novel model for language-driven semantic image segmentation. We use a text encoder to compute embeddings of descriptive input labels. The encoder is trained with a contrastive objective to align pixel embeddings to the text embedding of the corresponding semantic class.
  arXiv  Detail & Related papers  (2022-01-10T18:59:10Z)
• CRIS: CLIP-Driven Referring Image Segmentation [71.56466057776086]
  We propose an end-to-end CLIP-Driven Referring Image framework (CRIS) CRIS resorts to vision-language decoding and contrastive learning for achieving the text-to-pixel alignment. Our proposed framework significantly outperforms the state-of-the-art performance without any post-processing.
  arXiv  Detail & Related papers  (2021-11-30T07:29:08Z)

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.