Text4Seg: Reimagining Image Segmentation as Text Generation

• URL: http://arxiv.org/abs/2410.09855v1
• Date: Sun, 13 Oct 2024 14:28:16 GMT
• Title: Text4Seg: Reimagining Image Segmentation as Text Generation
• Authors: Mengcheng Lan, Chaofeng Chen, Yue Zhou, Jiaxing Xu, Yiping Ke, Xinjiang Wang, Litong Feng, Wayne Zhang,
• Abstract summary: We introduce Text4Seg, a novel text-as-mask paradigm that casts image segmentation as a text generation problem. Key innovation is semantic descriptors, a new textual representation of segmentation masks where each image patch is mapped to its corresponding text label. We show that Text4Seg achieves state-of-the-art performance on multiple datasets by fine-tuning different MLLM backbones.
• Score: 32.230379277018194
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Large Language Models (MLLMs) have shown exceptional capabilities in vision-language tasks; however, effectively integrating image segmentation into these models remains a significant challenge. In this paper, we introduce Text4Seg, a novel text-as-mask paradigm that casts image segmentation as a text generation problem, eliminating the need for additional decoders and significantly simplifying the segmentation process. Our key innovation is semantic descriptors, a new textual representation of segmentation masks where each image patch is mapped to its corresponding text label. This unified representation allows seamless integration into the auto-regressive training pipeline of MLLMs for easier optimization. We demonstrate that representing an image with $16\times16$ semantic descriptors yields competitive segmentation performance. To enhance efficiency, we introduce the Row-wise Run-Length Encoding (R-RLE), which compresses redundant text sequences, reducing the length of semantic descriptors by 74% and accelerating inference by $3\times$, without compromising performance. Extensive experiments across various vision tasks, such as referring expression segmentation and comprehension, show that Text4Seg achieves state-of-the-art performance on multiple datasets by fine-tuning different MLLM backbones. Our approach provides an efficient, scalable solution for vision-centric tasks within the MLLM framework.

Related papers

• AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene Understanding [96.01726275876548]
  We present AdaptVision, a multimodal large language model specifically designed to dynamically process input images at varying resolutions. We devise a dynamic image partitioning module that adjusts the number of visual tokens according to the size and aspect ratio of images. Our model is capable of processing images with resolutions up to $1008times 1008$.
  arXiv  Detail & Related papers  (2024-08-30T03:16:49Z)
• LLM4GEN: Leveraging Semantic Representation of LLMs for Text-to-Image Generation [30.897935761304034]
  We propose a novel framework called textbfLLM4GEN, which enhances the semantic understanding of text-to-image diffusion models. A specially designed Cross-Adapter Module (CAM) integrates the original text features of text-to-image models with LLM features. DensePrompts, which contains $7,000$ dense prompts, provides a comprehensive evaluation for the text-to-image generation task.
  arXiv  Detail & Related papers  (2024-06-30T15:50:32Z)
• Towards Semantic Equivalence of Tokenization in Multimodal LLM [149.11720372278273]
  Vision tokenization is essential for semantic alignment between vision and language. This paper proposes a novel dynamic Semantic-Equivalent Vision Tokenizer (SeTok) SeTok groups visual features into semantic units via a dynamic clustering algorithm. The resulting vision tokens effectively preserve semantic integrity and capture both low-frequency and high-frequency visual features.
  arXiv  Detail & Related papers  (2024-06-07T17:55:43Z)
• Generalizable Entity Grounding via Assistance of Large Language Model [77.07759442298666]
  We propose a novel approach to densely ground visual entities from a long caption. We leverage a large multimodal model to extract semantic nouns, a class-a segmentation model to generate entity-level segmentation, and a multi-modal feature fusion module to associate each semantic noun with its corresponding segmentation mask.
  arXiv  Detail & Related papers  (2024-02-04T16:06:05Z)
• LightCLIP: Learning Multi-Level Interaction for Lightweight Vision-Language Models [45.672539931681065]
  We propose a multi-level interaction paradigm for training lightweight CLIP models. An auxiliary fusion module injecting unmasked image embedding into masked text embedding is proposed.
  arXiv  Detail & Related papers  (2023-12-01T15:54:55Z)
• Segment Everything Everywhere All at Once [124.90835636901096]
  We present SEEM, a promptable and interactive model for segmenting everything everywhere all at once in an image. We propose a novel decoding mechanism that enables diverse prompting for all types of segmentation tasks. We conduct a comprehensive empirical study to validate the effectiveness of SEEM across diverse segmentation tasks.
  arXiv  Detail & Related papers  (2023-04-13T17:59:40Z)
• 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)
• 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.