2019 IEEE International Conference on Computer Vision
AInnovation published the paper "HM-NAS: Efficient Neural Architecture Search via Hierarchical Masking" and was best nominated by the workshop. The paper proposed a search method using hierarchical masks to make model training faster, model parameters less, and model network structure. It is better and requires less computing power. It only takes 1-2 GPUs for one day of training to complete the training of the model.