Guocheng qian

Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning featured image
Deep Learning

Dr<sup>2</sup>Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning

Large pretrained models are increasingly crucial in modern computer vision tasks. These models are typically used in downstream tasks by end-to-end finetuning, which is highly …

avatar
Chen Zhao
•
Read more
When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search featured image
Deep Learning

When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search

The key challenge in neural architecture search (NAS) is designing how to explore wisely in the huge search space. We propose a new NAS method called TNAS (NAS with trees), which …

Guocheng qian
•
Read more