ObjectAug: Object-level Data Augmentation for Semantic Image Segmentation

TL;DR

ObjectAug introduces object-level data augmentation for semantic image segmentation by decoupling, augmenting, and reassembling objects and backgrounds, leading to improved boundary exploration and segmentation accuracy.

Contribution

It proposes a novel object-level augmentation method that enhances boundary learning and can be combined with existing strategies for better segmentation results.

Findings

Significant improvement in segmentation accuracy on natural and medical datasets

Effective boundary exploration through object-level augmentation

Compatibility with existing augmentation methods enhances performance

Abstract

Semantic image segmentation aims to obtain object labels with precise boundaries, which usually suffers from overfitting. Recently, various data augmentation strategies like regional dropout and mix strategies have been proposed to address the problem. These strategies have proved to be effective for guiding the model to attend on less discriminative parts. However, current strategies operate at the image level, and objects and the background are coupled. Thus, the boundaries are not well augmented due to the fixed semantic scenario. In this paper, we propose ObjectAug to perform object-level augmentation for semantic image segmentation. ObjectAug first decouples the image into individual objects and the background using the semantic labels. Next, each object is augmented individually with commonly used augmentation methods (e.g., scaling, shifting, and rotation). Then, the black area brought by object augmentation is further restored using image inpainting. Finally, the augmented objects and background are assembled as an augmented image. In this way, the boundaries can be fully explored in the various semantic scenarios. In addition, ObjectAug can support category-aware augmentation that gives various possibilities to objects in each category, and can be easily combined with existing image-level augmentation methods to further boost performance. Comprehensive experiments are conducted on both natural image and medical image datasets. Experiment results demonstrate that our ObjectAug can evidently improve segmentation performance.