Awesome

INTERN-2.5: Multimodal Multitask General Large Model

The official implementation of

InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions.

[Paper] [Blog in Chinese]

Highlights

• :thumbsup: The strongest open-source visual universal backbone model with up to 3 billion parameters
• 🏆 Achieved 90.1% Top1 accuracy in ImageNet, the most accurate among open-source models
• 🏆 Achieved 65.5 mAP on the COCO benchmark dataset for object detection, the only model that exceeded 65.0 mAP

Related Projects

Foundation Models

• Uni-Perceiver: A Pre-training unified architecture for generic perception for zero-shot and few-shot tasks
• Uni-Perceiver v2: A generalist model for large-scale vision and vision-language tasks
• M3I-Pretraining: One-stage pre-training paradigm via maximizing multi-modal mutual information
• InternVL: The largest open-source vision/vision-language foundation model (14B) to date

Autonomous Driving

• BEVFormer: A cutting-edge baseline for camera-based 3D detection
• BEVFormer v2: Adapting modern image backbones to Bird's-Eye-View recognition via perspective supervision

Application in Challenges

• 2022 Waymo 3D Camera-Only Detection Challenge: BEVFormer++ Ranks 1st based on InternImage
• nuScenes 3D detection task: BEVFormer v2 achieves SOTA performance of 64.8 NDS on nuScenes Camera Only
• CVPR 2023 Workshop End-to-End Autonomous Driving: InternImage supports the baseline of the 3D Occupancy Prediction Challenge and OpenLane Topology Challenge

News

• Jan 22, 2024: 🚀 Support DCNv4 in InternImage!
• Mar 14, 2023: 🚀 "INTERN-2.5" is released！
• Feb 28, 2023: 🚀 InternImage is accepted to CVPR 2023!
• Nov 18, 2022: 🚀 InternImage-XL merged into BEVFormer v2 achieves state-of-the-art performance of 63.4 NDS on nuScenes Camera Only.
• Nov 10, 2022: 🚀 InternImage-H achieves a new record 65.4 mAP on COCO detection test-dev and 62.9 mIoU on ADE20K, outperforming previous models by a large margin.

History

• Models/APIs for other downstream tasks
• Support CVPR 2023 Workshop on End-to-End Autonomous Driving, see here
• Support Segment Anything
• Support extracting intermediate features, see here
• Low-cost training with DeepSpeed, see here
• Compiling-free .whl package of DCNv3 operator, see here
• InternImage-H(1B)/G(3B)
• TensorRT inference for classification/detection/segmentation models
• Classification code of the InternImage series
• InternImage-T/S/B/L/XL ImageNet-1K pretrained model
• InternImage-L/XL ImageNet-22K pretrained model
• InternImage-T/S/B/L/XL detection and instance segmentation model
• InternImage-T/S/B/L/XL semantic segmentation model

Introduction

"INTERN-2.5" is a powerful multimodal multitask general model jointly released by SenseTime and Shanghai AI Laboratory. It consists of large-scale vision foundation model "InternImage", pre-training method "M3I-Pretraining", generic decoder "Uni-Perceiver" series, and generic encoder for autonomous driving perception "BEVFormer" series.

Applications

🌅 Image Modality Tasks

"INTERN-2.5" achieved an impressive Top-1 accuracy of 90.1% on the ImageNet benchmark dataset using only publicly available data for image classification. Apart from two undisclosed models trained with additional datasets by Google and Microsoft, "INTERN-2.5" is the only open-source model that achieves a Top-1 accuracy of over 90.0%, and it is also the largest model in scale worldwide.

"INTERN-2.5" outperformed all other models worldwide on the COCO object detection benchmark dataset with a remarkable mAP of 65.5, making it the only model that surpasses 65 mAP in the world.

"INTERN-2.5" also demonstrated world's best performance on 16 other important visual benchmark datasets, covering a wide range of tasks such as classification, detection, and segmentation, making it the top-performing model across multiple domains.

Performance

• Classification

• Detection

• Segmentation

🌁 📖 Image and Text Cross-Modal Tasks

Image-Text Retrieval: "INTERN-2.5" can quickly locate and retrieve the most semantically relevant images based on textual content requirements. This capability can be applied to both videos and image collections and can be further combined with object detection boxes to enable a variety of applications, helping users quickly and easily find the required image resources. For example, it can return the relevant images specified by the text in the album.

Image-To-Text: "INTERN-2.5" has a strong understanding capability in various aspects of visual-to-text tasks such as image captioning, visual question answering, visual reasoning, and optical character recognition. For example, in the context of autonomous driving, it can enhance the scene perception and understanding capabilities, assist the vehicle in judging traffic signal status, road signs, and other information, and provide effective perception information support for vehicle decision-making and planning.

Performance

Released Models

Export classification model from pytorch to tensorrt

Export detection model from pytorch to tensorrt

Export segmentation model from pytorch to tensorrt

Before using mmdeploy to convert our PyTorch models to TensorRT, please make sure you have the DCNv3 custom operator builded correctly. You can build it with the following command:

export MMDEPLOY_DIR=/the/root/path/of/MMDeploy

# prepare our custom ops, you can find it at InternImage/tensorrt/modulated_deform_conv_v3
cp -r modulated_deform_conv_v3 ${MMDEPLOY_DIR}/csrc/mmdeploy/backend_ops/tensorrt

# build custom ops
cd ${MMDEPLOY_DIR}
mkdir -p build && cd build
cmake -DCMAKE_CXX_COMPILER=g++-7 -DMMDEPLOY_TARGET_BACKENDS=trt -DTENSORRT_DIR=${TENSORRT_DIR} -DCUDNN_DIR=${CUDNN_DIR} ..
make -j$(nproc) && make install

# install the mmdeploy after building custom ops
cd ${MMDEPLOY_DIR}
pip install -e .

For more details on building custom ops, please refering to this document.

Citations

If this work is helpful for your research, please consider citing the following BibTeX entry.

@article{wang2022internimage,
  title={InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions},
  author={Wang, Wenhai and Dai, Jifeng and Chen, Zhe and Huang, Zhenhang and Li, Zhiqi and Zhu, Xizhou and Hu, Xiaowei and Lu, Tong and Lu, Lewei and Li, Hongsheng and others},
  journal={arXiv preprint arXiv:2211.05778},
  year={2022}
}

@inproceedings{zhu2022uni,
  title={Uni-perceiver: Pre-training unified architecture for generic perception for zero-shot and few-shot tasks},
  author={Zhu, Xizhou and Zhu, Jinguo and Li, Hao and Wu, Xiaoshi and Li, Hongsheng and Wang, Xiaohua and Dai, Jifeng},
  booktitle={CVPR},
  pages={16804--16815},
  year={2022}
}

@article{zhu2022uni,
  title={Uni-perceiver-moe: Learning sparse generalist models with conditional moes},
  author={Zhu, Jinguo and Zhu, Xizhou and Wang, Wenhai and Wang, Xiaohua and Li, Hongsheng and Wang, Xiaogang and Dai, Jifeng},
  journal={arXiv preprint arXiv:2206.04674},
  year={2022}
}

@article{li2022uni,
  title={Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks},
  author={Li, Hao and Zhu, Jinguo and Jiang, Xiaohu and Zhu, Xizhou and Li, Hongsheng and Yuan, Chun and Wang, Xiaohua and Qiao, Yu and Wang, Xiaogang and Wang, Wenhai and others},
  journal={arXiv preprint arXiv:2211.09808},
  year={2022}
}

@article{yang2022bevformer,
  title={BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision},
  author={Yang, Chenyu and Chen, Yuntao and Tian, Hao and Tao, Chenxin and Zhu, Xizhou and Zhang, Zhaoxiang and Huang, Gao and Li, Hongyang and Qiao, Yu and Lu, Lewei and others},
  journal={arXiv preprint arXiv:2211.10439},
  year={2022}
}

@article{su2022towards,
  title={Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information},
  author={Su, Weijie and Zhu, Xizhou and Tao, Chenxin and Lu, Lewei and Li, Bin and Huang, Gao and Qiao, Yu and Wang, Xiaogang and Zhou, Jie and Dai, Jifeng},
  journal={arXiv preprint arXiv:2211.09807},
  year={2022}
}

@inproceedings{li2022bevformer,
  title={Bevformer: Learning bird’s-eye-view representation from multi-camera images via spatiotemporal transformers},
  author={Li, Zhiqi and Wang, Wenhai and Li, Hongyang and Xie, Enze and Sima, Chonghao and Lu, Tong and Qiao, Yu and Dai, Jifeng},
  booktitle={ECCV},
  pages={1--18},
  year={2022},
}