$\alpha$ DARTS Once More: Enhancing Differentiable Architecture Search by Masked Image Modeling

TL;DR

This paper enhances differentiable architecture search (DARTS) by integrating masked image modeling to incorporate semantic information, leading to improved architecture discovery and state-of-the-art results on multiple datasets.

Contribution

It introduces a novel patch recovery approach using masked image modeling to inject semantic information into DARTS, overcoming limitations of previous methods that relied solely on classification labels.

Findings

Surpasses all previous DARTS variants in performance.

Achieves state-of-the-art results on CIFAR-10, CIFAR-100, and ImageNet.

Does not require complex manual-designed strategies.

Abstract

Differentiable architecture search (DARTS) has been a mainstream direction in automatic machine learning. Since the discovery that original DARTS will inevitably converge to poor architectures, recent works alleviate this by either designing rule-based architecture selection techniques or incorporating complex regularization techniques, abandoning the simplicity of the original DARTS that selects architectures based on the largest parametric value, namely $\alpha$. Moreover, we find that all the previous attempts only rely on classification labels, hence learning only single modal information and limiting the representation power of the shared network. To this end, we propose to additionally inject semantic information by formulating a patch recovery approach. Specifically, we exploit the recent trending masked image modeling and do not abandon the guidance from the downstream tasks during the search phase. Our method surpasses all previous DARTS variants and achieves state-of-the-art results on CIFAR-10, CIFAR-100, and ImageNet without complex manual-designed strategies.