IDA: Improved Data Augmentation Applied to Salient Object Detection

TL;DR

This paper introduces an improved data augmentation technique for salient object detection that enhances training data diversity, leading to better segmentation performance across multiple datasets.

Contribution

The proposed IDA method combines inpainting, affine transformations, and background optimization to improve data augmentation for SOD, surpassing traditional techniques.

Findings

Enhanced segmentation quality on several SOD datasets.

Surpassed traditional augmentation methods in F-measure and Precision.

Achieved higher average ranking across multiple evaluation metrics.

Abstract

In this paper, we present an Improved Data Augmentation (IDA) technique focused on Salient Object Detection (SOD). Standard data augmentation techniques proposed in the literature, such as image cropping, rotation, flipping, and resizing, only generate variations of the existing examples, providing a limited generalization. Our method combines image inpainting, affine transformations, and the linear combination of different generated background images with salient objects extracted from labeled data. Our proposed technique enables more precise control of the object's position and size while preserving background information. The background choice is based on an inter-image optimization, while object size follows a uniform random distribution within a specified interval, and the object position is intra-image optimal. We show that our method improves the segmentation quality when used for training state-of-the-art neural networks on several famous datasets of the SOD field. Combining our method with others surpasses traditional techniques such as horizontal-flip in 0.52% for F-measure and 1.19% for Precision. We also provide an evaluation in 7 different SOD datasets, with 9 distinct evaluation metrics and an average ranking of the evaluated methods.