---
title: sam3-litetext-s1
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/sam3-litetext-s1"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/sam3-litetext-s1.md"
repository: AI-ModelScope/sam3-litetext-s1
last_updated: 2026-04-21
license: apache-2.0
model_type:
  - sam3_lite_text
architectures:
  - Sam3LiteTextModel
parameters: 550.2M
tensor_type:
  - F32
library_name:
  - transformer
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 57
stars: 0
---

# sam3-litetext-s1

> sam3-litetext-s1 - AI-ModelScope 在 ModelScope 开源的模型。SAM3-LiteText was proposed in SAM3-LiteText: An Anatomical Study of the SAM3 Text Encoder for Efficient Vision-Language Segmentation by Chengxi Zeng, Yuxuan Jiang, Ge Gao, Shuai Wang, Duolikun Danier, Bin…

AI-ModelScope/sam3-litetext-s1 是 ModelScope 魔搭社区上的 550.2M 参数机器学习模型，采用 apache-2.0 许可。

- **Repository**: AI-ModelScope/sam3-litetext-s1
- **License**: apache-2.0
- **Parameters**: 550.2M
- **Downloads**: 57
- **Stars**: 0
- **Last updated**: 2026-04-21

Source: https://www.modelscope.cn/models/AI-ModelScope/sam3-litetext-s1

---

# SAM3-LiteText

## Overview

SAM3-LiteText was proposed in [SAM3-LiteText: An Anatomical Study of the SAM3 Text Encoder for Efficient Vision-Language Segmentation](https://huggingface.co/papers/2602.12173) by Chengxi Zeng, Yuxuan Jiang, Ge Gao, Shuai Wang, Duolikun Danier, Bin Zhu, Stevan Rudinac, David Bull, and Fan Zhang.

SAM3-LiteText is a lightweight variant of SAM3 that replaces the heavy SAM3 text encoder (353M parameters) with a compact MobileCLIP-based text encoder optimized through knowledge distillation. The SAM3 ViT-H image encoder is kept intact. This reduces text encoder parameters by up to 88% while maintaining segmentation performance comparable to the original model.

The abstract from the paper is the following:

*Vision-language segmentation models such as SAM3 enable flexible, prompt-driven visual grounding, but inherit large, general-purpose text encoders originally designed for open-ended language understanding. In practice, segmentation prompts are short, structured, and semantically constrained, leading to substantial over-provisioning in text encoder capacity and persistent computational and memory overhead. In this paper, we perform a large-scale anatomical analysis of text prompting in vision-language segmentation, covering 404,796 real prompts across multiple benchmarks. Our analysis reveals severe redundancy: most context windows are underutilized, vocabulary usage is highly sparse, and text embeddings lie on low-dimensional manifold despite high-dimensional representations. Motivated by these findings, we propose SAM3-LiteText, a lightweight text encoding framework that replaces the original SAM3 text encoder with a compact MobileCLIP student that is optimized by knowledge distillation. Extensive experiments on image and video segmentation benchmarks show that SAM3-LiteText reduces text encoder parameters by up to 88%, substantially reducing static memory footprint, while maintaining segmentation performance comparable to the original model.*

The text encoder architecture is based on [MobileCLIP](https://huggingface.co/papers/2311.17049) and comes in three variants:

| Variant | Text Encoder | Text Params | Reduction |
|---|---|---|---|
| SAM3-LiteText-S0-16 | MobileCLIP-S0 | 42.54M | ~88% |
| SAM3-LiteText-S1-16 | MobileCLIP-S1 | 63.53M | ~82% |
| SAM3-LiteText-L-16 | MobileCLIP2-L | 123.80M | ~65% |

## Usage

SAM3-LiteText is a drop-in replacement for SAM3 with a lightweight text encoder. It uses the same processor and supports the same prompting interface. Refer to the [SAM3 documentation](sam3) for detailed usage examples including text prompts, box prompts, batched inference, and more.

```python
from io import BytesIO

import httpx
from transformers import AutoModel, AutoProcessor
from PIL import Image

model = AutoModel.from_pretrained("Simon7108528/sam3-litetext-s1", device_map="auto")
processor = AutoProcessor.from_pretrained("Simon7108528/sam3-litetext-s1")

image_url = "http://images.cocodataset.org/val2017/000000077595.jpg"
image = Image.open(BytesIO(httpx.get(image_url).content)).convert("RGB")

inputs = processor(images=image, text="ear", return_tensors="pt").to(model.device)

outputs = model(**inputs)

results = processor.post_process_instance_segmentation(
    outputs,
    threshold=0.5,
    mask_threshold=0.5,
    target_sizes=inputs.get("original_sizes").tolist(),
)[0]

print(f"Found {len(results['masks'])} objects")
```