https://github.com/nvlabs/mambavision
[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone
https://github.com/nvlabs/mambavision
deep-learning foundation-models huggingface-transformers hybrid-models image-classification instance-segmentation mamba object-detection self-attention semantic-segmentation transformers vision-transformer visual-recognition
Last synced: 9 months ago
JSON representation
[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone
- Host: GitHub
- URL: https://github.com/nvlabs/mambavision
- Owner: NVlabs
- License: other
- Created: 2024-06-10T17:46:08.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2025-07-22T22:12:11.000Z (10 months ago)
- Last Synced: 2025-07-23T00:13:31.719Z (10 months ago)
- Topics: deep-learning, foundation-models, huggingface-transformers, hybrid-models, image-classification, instance-segmentation, mamba, object-detection, self-attention, semantic-segmentation, transformers, vision-transformer, visual-recognition
- Language: Python
- Homepage: https://arxiv.org/abs/2407.08083
- Size: 2.76 MB
- Stars: 1,607
- Watchers: 18
- Forks: 85
- Open Issues: 17
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# MambaVision: A Hybrid Mamba-Transformer Vision Backbone
Official PyTorch implementation of [**MambaVision: A Hybrid Mamba-Transformer Vision Backbone**](https://arxiv.org/abs/2407.08083).
[](https://github.com/NVlabs/MambaVision/stargazers)
[Ali Hatamizadeh](https://research.nvidia.com/person/ali-hatamizadeh) and
[Jan Kautz](https://jankautz.com/).
For business inquiries, please visit our website and submit the form: [NVIDIA Research Licensing](https://www.nvidia.com/en-us/research/inquiries/)
Try MambaVision: [](https://colab.research.google.com/drive/1WR8LAzRMoK19RiFA-Br0Xxir_Htb3pLf)
---
MambaVision demonstrates a strong performance by achieving a new SOTA Pareto-front in
terms of Top-1 accuracy and throughput.
We introduce a novel mixer block by creating a symmetric path without SSM to enhance the modeling of global context:
MambaVision has a hierarchical architecture that employs both self-attention and mixer blocks:
## 💥 News 💥
- **[06.10.2025]** The MambaVision [poster](https://github.com/NVlabs/MambaVision/blob/main/mambavision/assets/mamba_vision_poster_cvpr25.pdf) will be presented in CVPR 2025 in Nashville on Sunday, June 15, 2025, from 10:30 a.m. to 12:30 p.m. CDT in Exhibit Hall D, Poster #403.
- **[06.10.2025]** Semantic segmentation code and models released [here](https://github.com/NVlabs/MambaVision/tree/main/semantic_segmentation) !
- **[06.07.2025]** Object detection code and models released [here](https://github.com/NVlabs/MambaVision/tree/main/object_detection) !
- **[03.29.2025]** You can now easily run MambaVision in Google Colab. Try here: [](https://colab.research.google.com/drive/1WR8LAzRMoK19RiFA-Br0Xxir_Htb3pLf)
- **[03.29.2025]** New MambaVision [pip package](https://pypi.org/project/mambavision/) released !
- **[03.25.2025]** Updated [manuscript](https://arxiv.org/pdf/2407.08083) is now available on arXiv !
- **[03.25.2025]** 21K models and code added to the repository.
- **[03.25.2025]** MambaVision is the **first** mamba-based vision backbone at scale !
- **[03.24.2025]** [MambaVision-L3-512-21K](https://huggingface.co/nvidia/MambaVision-L3-512-21K) achieves a **Top-1 accuracy of 88.1** %
- **[03.24.2025]** New ImageNet-21K models have been added to [MambaVision Hugging Face collection](https://huggingface.co/collections/nvidia/mambavision-66943871a6b36c9e78b327d3)
- **[02.26.2025]** MambaVision has been accepted to CVPR 2025 !
- **[07.24.2024]** MambaVision [Hugging Face](https://huggingface.co/collections/nvidia/mambavision-66943871a6b36c9e78b327d3) models are released !
- **[07.14.2024]** We added support for processing any resolution images.
- **[07.12.2024]** [Paper](https://arxiv.org/abs/2407.08083) is now available on arXiv !
- **[07.11.2024]** [Mambavision pip package](https://pypi.org/project/mambavision/) is released !
- **[07.10.2024]** We have released the code and model checkpoints for Mambavision !
## Quick Start
### Google Colab
You can simply try image classification with MambaVision in Google Colab: [](https://colab.research.google.com/drive/1WR8LAzRMoK19RiFA-Br0Xxir_Htb3pLf)
### Hugging Face (Classification + Feature extraction)
Pretrained MambaVision models can be simply used via [Hugging Face](https://huggingface.co/collections/nvidia/mambavision-66943871a6b36c9e78b327d3) library with **a few lines of code**. First install the requirements:
```bash
pip install mambavision
```
The model can be simply imported:
```python
>>> from transformers import AutoModelForImageClassification
>>> model = AutoModelForImageClassification.from_pretrained("nvidia/MambaVision-T-1K", trust_remote_code=True)
```
We demonstrate an end-to-end image classification example in the following.
Given the following image from [COCO dataset](https://cocodataset.org/#home) val set as an input:
The following snippet can be used:
```python
from transformers import AutoModelForImageClassification
from PIL import Image
from timm.data.transforms_factory import create_transform
import requests
model = AutoModelForImageClassification.from_pretrained("nvidia/MambaVision-T-1K", trust_remote_code=True)
# eval mode for inference
model.cuda().eval()
# prepare image for the model
url = 'http://images.cocodataset.org/val2017/000000020247.jpg'
image = Image.open(requests.get(url, stream=True).raw)
input_resolution = (3, 224, 224) # MambaVision supports any input resolutions
transform = create_transform(input_size=input_resolution,
is_training=False,
mean=model.config.mean,
std=model.config.std,
crop_mode=model.config.crop_mode,
crop_pct=model.config.crop_pct)
inputs = transform(image).unsqueeze(0).cuda()
# model inference
outputs = model(inputs)
logits = outputs['logits']
predicted_class_idx = logits.argmax(-1).item()
print("Predicted class:", model.config.id2label[predicted_class_idx])
```
The predicted label is brown bear, bruin, Ursus arctos.
You can also use Hugging Face MambaVision models for feature extraction. The model provides the outputs of each stage of model (hierarchical multi-scale features in 4 stages) as well as the final averaged-pool features that are flattened. The former is used for downstream tasks such as classification and detection.
The following snippet can be used for feature extraction:
```Python
from transformers import AutoModel
from PIL import Image
from timm.data.transforms_factory import create_transform
import requests
model = AutoModel.from_pretrained("nvidia/MambaVision-T-1K", trust_remote_code=True)
# eval mode for inference
model.cuda().eval()
# prepare image for the model
url = 'http://images.cocodataset.org/val2017/000000020247.jpg'
image = Image.open(requests.get(url, stream=True).raw)
input_resolution = (3, 224, 224) # MambaVision supports any input resolutions
transform = create_transform(input_size=input_resolution,
is_training=False,
mean=model.config.mean,
std=model.config.std,
crop_mode=model.config.crop_mode,
crop_pct=model.config.crop_pct)
inputs = transform(image).unsqueeze(0).cuda()
# model inference
out_avg_pool, features = model(inputs)
print("Size of the averaged pool features:", out_avg_pool.size()) # torch.Size([1, 640])
print("Number of stages in extracted features:", len(features)) # 4 stages
print("Size of extracted features in stage 1:", features[0].size()) # torch.Size([1, 80, 56, 56])
print("Size of extracted features in stage 4:", features[3].size()) # torch.Size([1, 640, 7, 7])
```
Currently, we offer [MambaVision-T-1K](https://huggingface.co/nvidia/MambaVision-T-1K), [MambaVision-T2-1K](https://huggingface.co/nvidia/MambaVision-T2-1K), [MambaVision-S-1K](https://huggingface.co/nvidia/MambaVision-S-1K), [MambaVision-B-1K](https://huggingface.co/nvidia/MambaVision-B-1K), [MambaVision-L-1K](https://huggingface.co/nvidia/MambaVision-L-1K) and [MambaVision-L2-1K](https://huggingface.co/nvidia/MambaVision-L2-1K) on Hugging Face. All models can also be viewed [here](https://huggingface.co/collections/nvidia/mambavision-66943871a6b36c9e78b327d3).
### Classification (pip package)
We can also import pre-trained MambaVision models from the pip package with **a few lines of code**:
```bash
pip install mambavision
```
A pretrained MambaVision model with default hyper-parameters can be created as in:
```python
>>> from mambavision import create_model
# Define mamba_vision_T model
>>> model = create_model('mamba_vision_T', pretrained=True, model_path="/tmp/mambavision_tiny_1k.pth.tar")
```
Available list of pretrained models include `mamba_vision_T`, `mamba_vision_T2`, `mamba_vision_S`, `mamba_vision_B`, `mamba_vision_L` and `mamba_vision_L2`.
We can also simply test the model by passing a dummy image with **any resolution**. The output is the logits:
```python
>>> import torch
>>> image = torch.rand(1, 3, 512, 224).cuda() # place image on cuda
>>> model = model.cuda() # place model on cuda
>>> output = model(image) # output logit size is [1, 1000]
```
Using the pretrained models from our pip package, you can simply run validation:
```
python validate_pip_model.py --model mamba_vision_T --data_dir=$DATA_PATH --batch-size $BS
```
## Results + Pretrained Models
### ImageNet-21K
Name
Acc@1(%)
Acc@5(%)
#Params(M)
FLOPs(G)
Resolution
HF
Download
MambaVision-B-21K
84.9
97.5
97.7
15.0
224x224
link
model
MambaVision-L-21K
86.1
97.9
227.9
34.9
224x224
link
model
MambaVision-L2-512-21K
87.3
98.4
241.5
196.3
512x512
link
model
MambaVision-L3-256-21K
87.3
98.3
739.6
122.3
256x256
link
model
MambaVision-L3-512-21K
88.1
98.6
739.6
489.1
512x512
link
model
### ImageNet-1K
Name
Acc@1(%)
Acc@5(%)
Throughput(Img/Sec)
Resolution
#Params(M)
FLOPs(G)
HF
Download
MambaVision-T
82.3
96.2
6298
224x224
31.8
4.4
link
model
MambaVision-T2
82.7
96.3
5990
224x224
35.1
5.1
link
model
MambaVision-S
83.3
96.5
4700
224x224
50.1
7.5
link
model
MambaVision-B
84.2
96.9
3670
224x224
97.7
15.0
link
model
MambaVision-L
85.0
97.1
2190
224x224
227.9
34.9
link
model
MambaVision-L2
85.3
97.2
1021
224x224
241.5
37.5
link
model
## Detection Results + Models
Backbone
Detector
Lr Schd
box mAP
mask mAP
#Params(M)
FLOPs(G)
Config
Log
Model Ckpt
MambaVision-T-1K
Cascade Mask R-CNN
3x
51.1
44.3
86
740
config
log
model
MambaVision-S-1K
Cascade Mask R-CNN
3x
52.3
45.2
108
828
config
log
model
MambaVision-B-1K
Cascade Mask R-CNN
3x
52.8
45.7
145
964
config
log
model
## Segmentation Results + Models
Backbone
Method
Lr Schd
mIoU
#Params(M)
FLOPs(G)
Config
Log
Model Ckpt
MambaVision-T-1K
UPerNet
160K
46.0
55
945
config
log
model
MambaVision-S-1K
UPerNet
160K
48.2
84
1135
config
log
model
MambaVision-B-1K
UPerNet
160K
49.1
126
1342
config
log
model
MambaVision-L3-512-21K
UPerNet
160K
53.2
780
3670
config
log
model
## Installation
We provide a [docker file](./Dockerfile). In addition, assuming that a recent [PyTorch](https://pytorch.org/get-started/locally/) package is installed, the dependencies can be installed by running:
```bash
pip install -r requirements.txt
```
## Evaluation
The MambaVision models can be evaluated on ImageNet-1K validation set using the following:
```
python validate.py \
--model
--checkpoint
--data_dir
--batch-size