NOSE Augment: Fast and Effective Data Augmentation Without Searching

1 Jan 2021  ·  Qingrui Li, Song Xie, Anıl Oymagil, Mustafa Furkan Eseoglu, Ziyin Zhang, CM Lee ·

Data augmentation has been widely used for enhancing the diversity of training data and model generalization. Different from traditional handcrafted methods, recent research introduced automated search for optimal data augmentation policies and achieved state-of-the-art results on image classification tasks. However, these search-based implementations typically incur high computation cost and long search time because of large search spaces and complex searching algorithms. We revisited automated augmentation from alternate perspectives, such as increasing diversity and manipulating overall usage of augmented data. In this paper, we present an augmentation method without policy searching called NOSE Augment (NO SEarch Augment). Our method completely skips policy searching and instead adopts a stochastic policy strategy. To further boost the data diversity of stochastic augmentation, NOSE introduces new augmentation operations into the operation pool. We further propose the introduction of a multi-stage complexity driven strategy for ensuring a smooth convergence to a good quality model. We conduct extensive experiments and showed that our method could match or surpass state-of-the-art results provided by search-based methods in terms of accuracies. Without the need for policy search, our method is much more efficient than the existing AutoAugment series of implementations. Besides image classification task, we also examine the general validity of our proposed method by applying our method to Face Recognition and Optical Character Recognition (OCR) tasks. The results establish our proposed method as a fast and competitive data augmentation strategy that can be used across various CV tasks.

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods