Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers

• URL: http://arxiv.org/abs/2509.18096v1
• Date: Mon, 22 Sep 2025 17:59:54 GMT
• Title: Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers
• Authors: Chaehyun Kim, Heeseong Shin, Eunbeen Hong, Heeji Yoon, Anurag Arnab, Paul Hongsuck Seo, Sunghwan Hong, Seungryong Kim,
• Abstract summary: Text-to-image diffusion models excel at translating language prompts into implicitly grounding concepts through their cross-modal attention mechanisms.<n>Recent multi-modal diffusion transformers extend this by introducing joint self-attentiond image and text tokens, enabling richer and more scalable cross-modal alignment.<n>We introduce Seg4Diff, a systematic framework for analyzing the attention structures of MM-DiT, with a focus on how specific layers propagate semantic information from text to image.
• Score: 56.76198904599581
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-image diffusion models excel at translating language prompts into photorealistic images by implicitly grounding textual concepts through their cross-modal attention mechanisms. Recent multi-modal diffusion transformers extend this by introducing joint self-attention over concatenated image and text tokens, enabling richer and more scalable cross-modal alignment. However, a detailed understanding of how and where these attention maps contribute to image generation remains limited. In this paper, we introduce Seg4Diff (Segmentation for Diffusion), a systematic framework for analyzing the attention structures of MM-DiT, with a focus on how specific layers propagate semantic information from text to image. Through comprehensive analysis, we identify a semantic grounding expert layer, a specific MM-DiT block that consistently aligns text tokens with spatially coherent image regions, naturally producing high-quality semantic segmentation masks. We further demonstrate that applying a lightweight fine-tuning scheme with mask-annotated image data enhances the semantic grouping capabilities of these layers and thereby improves both segmentation performance and generated image fidelity. Our findings demonstrate that semantic grouping is an emergent property of diffusion transformers and can be selectively amplified to advance both segmentation and generation performance, paving the way for unified models that bridge visual perception and generation.

Related papers

• Text4Seg++: Advancing Image Segmentation via Generative Language Modeling [52.07442359419673]
  We propose a novel text-as-mask paradigm that casts image segmentation as a text generation problem.<n>Key innovation is semantic descriptors, a new textual representation of segmentation masks.<n>Experiments on natural and remote sensing datasets show that Text4Seg++ consistently outperforms state-of-the-art models.
  arXiv  Detail & Related papers  (2025-09-08T04:07:14Z)
• GS: Generative Segmentation via Label Diffusion [59.380173266566715]
  Language-driven image segmentation is a fundamental task in vision-language understanding, requiring models to segment regions of an image corresponding to natural language expressions.<n>Recent diffusion models have been introduced to this domain, but existing approaches remain image-centric.<n>We propose GS (Generative Label), a novel framework that formulates segmentation itself as a generative task.<n> Experimental results show that GS significantly outperforms existing discriminative and diffusion-based methods, setting a new state-of-the-art for language-driven segmentation.
  arXiv  Detail & Related papers  (2025-08-27T16:28:15Z)
• TeSG: Textual Semantic Guidance for Infrared and Visible Image Fusion [55.34830989105704]
  Infrared and visible image fusion (IVF) aims to combine complementary information from both image modalities.<n>We introduce textual semantics at two levels: the mask semantic level and the text semantic level.<n>We propose Textual Semantic Guidance for infrared and visible image fusion, which guides the image synthesis process.
  arXiv  Detail & Related papers  (2025-06-20T03:53:07Z)
• Scale-wise Bidirectional Alignment Network for Referring Remote Sensing Image Segmentation [12.893224628061516]
  The goal of referring remote sensing image segmentation (RRSIS) is to extract specific pixel-level regions within an aerial image via a natural language expression.<n>We propose an innovative framework called Scale-wise Bidirectional Alignment Network (SBANet) to address these challenges.<n>Our proposed method achieves superior performance in comparison to previous state-of-the-art methods on the RRSIS-D and RefSegRS datasets.
  arXiv  Detail & Related papers  (2025-01-01T14:24:04Z)
• InvSeg: Test-Time Prompt Inversion for Semantic Segmentation [33.60580908728705]
  InvSeg is a test-time prompt inversion method that tackles open-vocabulary semantic segmentation.<n>We introduce Contrastive Soft Clustering (CSC) to align derived masks with the image's structure information.<n>InvSeg learns context-rich text prompts in embedding space and achieves accurate semantic alignment across modalities.
  arXiv  Detail & Related papers  (2024-10-15T10:20:31Z)
• MaskDiffusion: Boosting Text-to-Image Consistency with Conditional Mask [84.84034179136458]
  A crucial factor leading to the text-image mismatch issue is the inadequate cross-modality relation learning. We propose an adaptive mask, which is conditioned on the attention maps and the prompt embeddings, to dynamically adjust the contribution of each text token to the image features. Our method, termed MaskDiffusion, is training-free and hot-pluggable for popular pre-trained diffusion models.
  arXiv  Detail & Related papers  (2023-09-08T15:53:37Z)
• Learning to Model Multimodal Semantic Alignment for Story Visualization [58.16484259508973]
  Story visualization aims to generate a sequence of images to narrate each sentence in a multi-sentence story. Current works face the problem of semantic misalignment because of their fixed architecture and diversity of input modalities. We explore the semantic alignment between text and image representations by learning to match their semantic levels in the GAN-based generative model.
  arXiv  Detail & Related papers  (2022-11-14T11:41:44Z)

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.