ResDNet: Efficient Dense Multi-Scale Representations With Residual Learning for High-Level Vision Tasks (TNNLS 2022)

The official implementation of our paper.

Model	ImageNet pre-trained weights
ResDNet-B-129	weights

If you find this repo is useful for your research or use the pre-trained weights, Please consider citing our paper:

@ARTICLE{9771050,
  author={Hong, Yuanduo and Pan, Huihui and Jia, Yisong and Sun, Weichao and Gao, Huijun},
  journal={IEEE Transactions on Neural Networks and Learning Systems}, 
  title={ResDNet: Efficient Dense Multi-Scale Representations With Residual Learning for High-Level Vision Tasks}, 
  year={2022},
  volume={},
  number={},
  pages={1-12},
  doi={10.1109/TNNLS.2022.3169779}}