---
title: mlcd-vit-base-patch32-224
canonical_url: "https://www.modelscope.cn/models/deepglint/mlcd-vit-base-patch32-224"
md_url: "https://www.modelscope.cn/models/deepglint/mlcd-vit-base-patch32-224.md"
repository: deepglint/mlcd-vit-base-patch32-224
last_updated: 2026-01-19
license: apache-2.0
model_type:
  - clip_vision_model
architectures:
  - CLIPVisionModel
parameters: 87.5M
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 47
stars: 0
---

# mlcd-vit-base-patch32-224

> mlcd-vit-base-patch32-224 - deepglint 在 ModelScope 开源的模型。[[Paper]](https://arxiv.org/abs/2407.17331) [[GitHub]](https://github.com/deepglint/unicom)

deepglint/mlcd-vit-base-patch32-224 是 ModelScope 魔搭社区上的 87.5M 参数机器学习模型，采用 apache-2.0 许可。

- **Repository**: deepglint/mlcd-vit-base-patch32-224
- **License**: apache-2.0
- **Parameters**: 87.5M
- **Downloads**: 47
- **Stars**: 0
- **Last updated**: 2026-01-19

Source: https://www.modelscope.cn/models/deepglint/mlcd-vit-base-patch32-224

---

[[Paper]](https://arxiv.org/abs/2407.17331) [[GitHub]](https://github.com/deepglint/unicom)  

This model is trained using the COYO700M dataset. The results below are from linear probe evaluations, demonstrating the model's performance on various benchmarks.

| Dataset   | CLIP | MLCD |
|-----------|------|------|
| Food101   | 88.8 | <span style="color:red">90.2</span> |
| CIFAR10   | 95.1 | <span style="color:red">96.9</span> |
| CIFAR100  | 80.5 | <span style="color:red">86.8</span> |
| Birdsnap  | 58.5 | <span style="color:red">72.1</span> |
| SUN397    | 76.6 | <span style="color:red">77.4</span> |
| Cars      | 81.8 | <span style="color:red">93.5</span> |
| Aircraft  | 52.0 | <span style="color:red">74.7</span> |
| VOC2007   | 87.7 | <span style="color:red">90.4</span> |
| DTD       | 76.5 | <span style="color:red">83.5</span> |
| Pets      | 90.0 | <span style="color:red">93.6</span> |
| Cal101    | 93.0 | <span style="color:red">97.7</span> |
| Flowers   | 96.9 | <span style="color:red">98.8</span> |
| ImageNet  | 76.1 | <span style="color:red">79.1</span> |