ANDA: A Novel Data Augmentation Technique Applied to Salient Object Detection

TL;DR

This paper introduces ANDA, a new data augmentation method for salient object detection that creates new images by combining objects with backgrounds, improving model performance significantly over existing techniques.

Contribution

The paper presents a novel augmentation technique that generates new training images by blending salient objects with backgrounds, enhancing generalization in salient object detection models.

Findings

Up to 14.1% improvement in F-measure

Reduction of up to 2.6% in Mean Absolute Error

Outperforms existing augmentation methods

Abstract

In this paper, we propose a novel data augmentation technique (ANDA) applied to the Salient Object Detection (SOD) context. 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 has the novelty of creating new images, by combining an object with a new background while retaining part of its salience in this new context; To do so, the ANDA technique relies on the linear combination between labeled salient objects and new backgrounds, generated by removing the original salient object in a process known as image inpainting. Our proposed technique allows for more precise control of the object's position and size while preserving background information. Aiming to evaluate our proposed method, we trained multiple deep neural networks and compared the effect that our technique has in each one. We also compared our method with other data augmentation techniques. Our findings show that depending on the network improvement can be up to 14.1% in the F-measure and decay of up to 2.6% in the Mean Absolute Error.