MPViT : Multi-Path Vision Transformer for Dense Prediction

This repository inlcudes official implementations and model weights for MPViT.

[Arxiv] [BibTeX]

MPViT : Multi-Path Vision Transformer for Dense Prediction
🏛️️️🏫Youngwan Lee, 🏛️️️Jonghee Kim, 🏫Jeff Willette, 🏫Sung Ju Hwang
ETRI:classical_building:️, KAIST:school:

Abstract

We explore multi-scale patch embedding and multi-path structure, constructing the Multi-Path Vision Transformer (MPViT). MPViT embeds features of the same size (i.e., sequence length) with patches of different scales simultaneously by using overlapping convolutional patch embedding. Tokens of different scales are then independently fed into the Transformer encoders via multiple paths and the resulting features are aggregated, enabling both fine and coarse feature representations at the same feature level. Thanks to the diverse and multi-scale feature representations, our MPViTs scaling from Tiny(5M) to Base(73M) consistently achieve superior performance over state-of-the-art Vision Transformers on ImageNet classification, object detection, instance segmentation, and semantic segmentation. These extensive results demonstrate that MPViT can serve as a versatile backbone network for various vision tasks.

Main results on ImageNet-1K

🚀 These all models are trained on ImageNet-1K with the same training recipe as DeiT and CoaT.

model	resolution	acc@1	#params	FLOPs	weight
MPViT-T	224x224	78.2	5.8M	1.6G	weight
MPViT-XS	224x224	80.9	10.5M	2.9G	weight
MPViT-S	224x224	83.0	22.8M	4.7G	weight
MPViT-B	224x224	84.3	74.8M	16.4G	weight

Main results on COCO object detection

🚀 All model are trained using ImageNet-1K pretrained weights.

☀️ MS denotes the same multi-scale training augmentation as in Swin-Transformer which follows the MS augmentation as in DETR and Sparse-RCNN. Therefore, we also follows the official implementation of DETR and Sparse-RCNN which are also based on Detectron2.

Please refer to detectron2/ for the details.

Backbone	Method	lr Schd	box mAP	mask mAP	#params	FLOPS	weight
MPViT-T	RetinaNet	1x	41.8	-	17M	196G	model \| metrics
MPViT-XS	RetinaNet	1x	43.8	-	20M	211G	model \| metrics
MPViT-S	RetinaNet	1x	45.7	-	32M	248G	model \| metrics
MPViT-B	RetinaNet	1x	47.0	-	85M	482G	model \| metrics
MPViT-T	RetinaNet	MS+3x	44.4	-	17M	196G	model \| metrics
MPViT-XS	RetinaNet	MS+3x	46.1	-	20M	211G	model \| metrics
MPViT-S	RetinaNet	MS+3x	47.6	-	32M	248G	model \| metrics
MPViT-B	RetinaNet	MS+3x	48.3	-	85M	482G	model \| metrics

MPViT-T	Mask R-CNN	1x	42.2	39.0	28M	216G	model \| metrics
MPViT-XS	Mask R-CNN	1x	44.2	40.4	30M	231G	model \| metrics
MPViT-S	Mask R-CNN	1x	46.4	42.4	43M	268G	model \| metrics
MPViT-B	Mask R-CNN	1x	48.2	43.5	95M	503G	model \| metrics
MPViT-T	Mask R-CNN	MS+3x	44.8	41.0	28M	216G	model \| metrics
MPViT-XS	Mask R-CNN	MS+3x	46.6	42.3	30M	231G	model \| metrics
MPViT-S	Mask R-CNN	MS+3x	48.4	43.9	43M	268G	model \| metrics
MPViT-B	Mask R-CNN	MS+3x	49.5	44.5	95M	503G	model \| metrics

Deformable-DETR

All models are trained using the same training recipe.

Please refer to deformable_detr/ for the details.

backbone	box mAP	epochs	link
ResNet-50	44.5	50	-
CoaT-lite S	47.0	50	link
CoaT-S	48.4	50	link
MPViT-S	49.0	50	link

Main results on ADE20K Semantic segmentation

All model are trained using ImageNet-1K pretrained weight.

Please refer to semantic_segmentation/ for the details.

Backbone	Method	Crop Size	Lr Schd	mIoU	#params	FLOPs	weight
MPViT-S	UperNet	512x512	160K	48.3	52M	943G	weight
MPViT-B	UperNet	512x512	160K	50.3	105M	1185G	weight

Getting Started

✋ We use pytorch==1.7.0 torchvision==0.8.1 cuda==10.1 libraries on NVIDIA V100 GPUs. If you use different versions of cuda, you may obtain different accuracies, but the differences are negligible.

For Image Classification, please see GET_STARTED.md.
For Object Detection and Instance Segmentation, please see OBJECT_DETECTION.md.
For Semantic Segmentation, please see semantic_segmentation/README.md.

Acknowledgement

This repository is built using the Timm library, DeiT, CoaT, Detectron2, mmsegmentation repositories.

This work was supported by Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korean government (MSIT) (No. 2020-0-00004, Development of Previsional Intelligence based on Long-term Visual Memory Network and No. 2014-3-00123, Development of High Performance Visual BigData Discovery Platform for Large-Scale Realtime Data Analysis).

License

Please refer to MPViT LSA.

Citing MPViT

@article{lee2021mpvit,
      title={MPViT: Multi-Path Vision Transformer for Dense Prediction}, 
      author={Youngwan Lee and Jonghee Kim and Jeff Willette and Sung Ju Hwang},
      year={2021},
      journal={arXiv preprint arXiv:2112.11010}
}

chaos1992/MPViT