research
∙
07/20/2023
EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization
Mixed-Precision Quantization (MQ) can achieve a competitive accuracy-com...
share
research
∙
03/28/2023
DisWOT: Student Architecture Search for Distillation WithOut Training
Knowledge distillation (KD) is an effective training strategy to improve...
research
∙
01/24/2023
Progressive Meta-Pooling Learning for Lightweight Image Classification Model
Practical networks for edge devices adopt shallow depth and small convol...
research
∙
01/24/2023
RD-NAS: Enhancing One-shot Supernet Ranking Ability via Ranking Distillation from Zero-cost Proxies
Neural architecture search (NAS) has made tremendous progress in the aut...
research
∙
12/28/2022
OVO: One-shot Vision Transformer Search with Online distillation
Pure transformers have shown great potential for vision tasks recently. ...
research
∙
09/16/2022
ConvFormer: Closing the Gap Between CNN and Vision Transformers
Vision transformers have shown excellent performance in computer vision ...
research
∙
06/27/2022
Prior-Guided One-shot Neural Architecture Search
Neural architecture search methods seek optimal candidates with efficien...
research
∙
03/08/2022