DAAS: Differentiable Architecture and Augmentation Policy Search
release_qvet6o3mqjgr7dtgfjakero3iu
by
Xiaoxing Wang, Xiangxiang Chu, Junchi Yan, Xiaokang Yang
2022
Abstract
Neural architecture search (NAS) has been an active direction of automatic
machine learning (Auto-ML), aiming to explore efficient network structures. The
searched architecture is evaluated by training on datasets with fixed data
augmentation policies. However, recent works on auto-augmentation show that the
suited augmentation policies can vary over different structures. Therefore,
this work considers the possible coupling between neural architectures and data
augmentation and proposes an effective algorithm jointly searching for them.
Specifically, 1) for the NAS task, we adopt a single-path based differentiable
method with Gumbel-softmax reparameterization strategy due to its memory
efficiency; 2) for the auto-augmentation task, we introduce a novel search
method based on policy gradient algorithm, which can significantly reduce the
computation complexity. Our approach achieves 97.91% accuracy on CIFAR-10 and
76.6% Top-1 accuracy on ImageNet dataset, showing the outstanding performance
of our search algorithm.
In text/plain
format
Archived Files and Locations
application/pdf 402.9 kB
file_engtp7q5vjdejfmaeaaitmgn7m
|
arxiv.org (repository) web.archive.org (webarchive) |
2109.15273v2
access all versions, variants, and formats of this works (eg, pre-prints)