ConTNet (Convlution-Tranformer Network) is a neural network built by stacking convolutional layers and transformers alternately. This architecture is proposed in response to the following two issues: (1) The receptive field of convolution is limited by a local window (3x3), which potentially impairs the performance of ConvNets on downstream tasks. (2) Transformer-based models suffers from insufficient robustness, as a result, the training course requires multiple training tricks and tons of regularization strategies. In our ConTNet, these drawbacks are alleviated through the combination of convolution and transformer. Two perspectives are offered to understand the motivation. From the view of ConvNet, the transformer sub-layer is inserted between any two conv layers to enhance the non-local interactions of ConvNet. From the view of Transformer, the presence of convolution layers reintroduces the inductive bias as a cause of under-fitting. Through numerical experiments, we find that ConTNet achieves competitive performance on image recognition and downstream tasks. More notably, ConTNet can be optimized easily even in the same way as ResNet.

We give an example of one machine multi-gpus training.

CUDA_VISIBLE_DEVICES=0,1,2,3 python3 -m torch.distributed.launch --nproc_per_node=4 --master_port 29501 main.py --arch ConT-M --batch_size 256 --save_path debug_trial_cont_m --save_best True 

To validate a model, please add the arg --eval .

CUDA_VISIBLE_DEVICES=0 python3 -m torch.distributed.launch --nproc_per_node=1 --master_port 29501 main.py --arch ConT-M --batch_size 256 --save_path debug_trial --eval ./debug_trial_cont_m/checkpoint_bestTop1.pth

To implement resume training, please add the arg --resume.

CUDA_VISIBLE_DEVICES=0,1,2,3 python3 -m torch.distributed.launch --nproc_per_node=4 --master_port 29501 main.py --arch ConT-M --batch_size 256 --save_path debug_trial --save_best True --resume ./debug_trial_cont_m/checkpoint_bestTop1.pth

ImageNet-pretrained weights are available from Google Drive or Baidu Cloud(the code is 3k3s).

Note: ^* indicates training with strong augmentations(auto-augmentation and mixup).

Object detection results on COCO.

Instance segmentation results on Cityscapes based on Mask-RCNN.

Semantic segmentation results on cityscapes.

@article{yan2021contnet,
    title={ConTNet: Why not use convolution and transformer at the same time?},
    author={Haotian Yan and Zhe Li and Weijian Li and Changhu Wang and Ming Wu and Chuang Zhang},
    year={2021},
    journal={arXiv preprint arXiv:2104.13497}
}