2 papers
cs.CV2021
Improving Ranking Correlation of Supernet with Candidates Enhancement and Progressive Training
Ziwei Yang, Ruyi Zhang, Zhi Yang +3
One-shot neural architecture search (NAS) applies weight-sharing supernet to reduce the unaffordable computation overhead of automated architecture designing. However, the weight-s…
cs.CV2021
Cascade Bagging for Accuracy Prediction with Few Training Samples
Ruyi Zhang, Ziwei Yang, Zhi Yang +3
Accuracy predictor is trained to predict the validation accuracy of an network from its architecture encoding. It can effectively assist in designing networks and improving Neural…