Contrastive Self-supervised Neural Architecture Search
This addresses the problem of expensive data labeling in NAS for computer vision researchers, offering a novel method that is incremental but impactful.
The paper tackles the high computational and labeling costs in neural architecture search by proposing a self-supervised approach that uses contrastive learning on unlabeled data, achieving state-of-the-art results with improved efficiency in labeling cost, search time, and accuracy.
This paper proposes a novel cell-based neural architecture search algorithm (NAS), which completely alleviates the expensive costs of data labeling inherited from supervised learning. Our algorithm capitalizes on the effectiveness of self-supervised learning for image representations, which is an increasingly crucial topic of computer vision. First, using only a small amount of unlabeled train data under contrastive self-supervised learning allow us to search on a more extensive search space, discovering better neural architectures without surging the computational resources. Second, we entirely relieve the cost for labeled data (by contrastive loss) in the search stage without compromising architectures' final performance in the evaluation phase. Finally, we tackle the inherent discrete search space of the NAS problem by sequential model-based optimization via the tree-parzen estimator (SMBO-TPE), enabling us to reduce the computational expense response surface significantly. An extensive number of experiments empirically show that our search algorithm can achieve state-of-the-art results with better efficiency in data labeling cost, searching time, and accuracy in final validation.