Data Augmentation in Classification and Segmentation: A Survey and New Strategies

TLDR

Deep neural networks, especially convolutional neural networks, have transformed computer vision, yet their performance often hinges on large datasets, and data scarcity can cause overfitting, making data augmentation a key remedy. This paper surveys current data augmentation methods for classification and segmentation tasks and proposes novel strategies. The authors introduce a parameter‑free random local rotation technique that selects random circular regions and rotates them, offering a boundary‑friendly alternative that can also complement other augmentation methods. Experimental results show that this new strategy consistently outperforms traditional rotation in image classification.

Abstract

In the past decade, deep neural networks, particularly convolutional neural networks, have revolutionised computer vision. However, all deep learning models may require a large amount of data so as to achieve satisfying results. Unfortunately, the availability of sufficient amounts of data for real-world problems is not always possible, and it is well recognised that a paucity of data easily results in overfitting. This issue may be addressed through several approaches, one of which is data augmentation. In this paper, we survey the existing data augmentation techniques in computer vision tasks, including segmentation and classification, and suggest new strategies. In particular, we introduce a way of implementing data augmentation by using local information in images. We propose a parameter-free and easy to implement strategy, the random local rotation strategy, which involves randomly selecting the location and size of circular regions in the image and rotating them with random angles. It can be used as an alternative to the traditional rotation strategy, which generally suffers from irregular image boundaries. It can also complement other techniques in data augmentation. Extensive experimental results and comparisons demonstrated that the new strategy consistently outperformed its traditional counterparts in, for example, image classification.