Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.10465 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908318647189504 |
|---|---|
| author | Zhang, Tao Li, Xiangtai Huang, Zilong Li, Yanwei Lei, Weixian Deng, Xueqing Chen, Shihao Ji, Shunping Feng, Jiashi |
| author_facet | Zhang, Tao Li, Xiangtai Huang, Zilong Li, Yanwei Lei, Weixian Deng, Xueqing Chen, Shihao Ji, Shunping Feng, Jiashi |
| contents | Multimodal Large Language Models (MLLMs) achieve remarkable performance for fine-grained pixel-level understanding tasks. However, all the works rely heavily on extra components, such as vision encoder (CLIP), segmentation experts, leading to high system complexity and limiting model scaling. In this work, our goal is to explore a highly simplified MLLM without introducing extra components. Our work is motivated by the recent works on Single trAnsformer as a unified vIsion-Language Model (SAIL) design, where these works jointly learn vision tokens and text tokens in transformers. We present Pixel-SAIL, a single transformer for pixel-wise MLLM tasks. In particular, we present three technical improvements on the plain baseline. First, we design a learnable upsampling module to refine visual token features. Secondly, we propose a novel visual prompt injection strategy to enable the single transformer to understand visual prompt inputs and benefit from the early fusion of visual prompt embeddings and vision tokens. Thirdly, we introduce a vision expert distillation strategy to efficiently enhance the single transformer's fine-grained feature extraction capability. In addition, we have collected a comprehensive pixel understanding benchmark (PerBench), using a manual check. It includes three tasks: detailed object description, visual prompt-based question answering, and visual-text referring segmentation. Extensive experiments on four referring segmentation benchmarks, one visual prompt benchmark, and our PerBench show that our Pixel-SAIL achieves comparable or even better results with a much simpler pipeline. Code and model will be released at https://github.com/magic-research/Sa2VA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10465 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding Zhang, Tao Li, Xiangtai Huang, Zilong Li, Yanwei Lei, Weixian Deng, Xueqing Chen, Shihao Ji, Shunping Feng, Jiashi Computer Vision and Pattern Recognition Multimodal Large Language Models (MLLMs) achieve remarkable performance for fine-grained pixel-level understanding tasks. However, all the works rely heavily on extra components, such as vision encoder (CLIP), segmentation experts, leading to high system complexity and limiting model scaling. In this work, our goal is to explore a highly simplified MLLM without introducing extra components. Our work is motivated by the recent works on Single trAnsformer as a unified vIsion-Language Model (SAIL) design, where these works jointly learn vision tokens and text tokens in transformers. We present Pixel-SAIL, a single transformer for pixel-wise MLLM tasks. In particular, we present three technical improvements on the plain baseline. First, we design a learnable upsampling module to refine visual token features. Secondly, we propose a novel visual prompt injection strategy to enable the single transformer to understand visual prompt inputs and benefit from the early fusion of visual prompt embeddings and vision tokens. Thirdly, we introduce a vision expert distillation strategy to efficiently enhance the single transformer's fine-grained feature extraction capability. In addition, we have collected a comprehensive pixel understanding benchmark (PerBench), using a manual check. It includes three tasks: detailed object description, visual prompt-based question answering, and visual-text referring segmentation. Extensive experiments on four referring segmentation benchmarks, one visual prompt benchmark, and our PerBench show that our Pixel-SAIL achieves comparable or even better results with a much simpler pipeline. Code and model will be released at https://github.com/magic-research/Sa2VA. |
| title | Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.10465 |