Masking Salient Object Detection, a Mask Region-based Convolutional Neural Network Analysis for Segmentation of Salient Objects

Krinski, Bruno A.; Ruíz, Daniel; Machado, Guilherme Z.; Todt, Eduardo

doi:10.48550/arxiv.1909.08038

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We present our findings on four distinct neural networks: three Fully Convolutional Networks (FCNs) with Residual Network (ResNet)-50, ResNet-101, and VGG-16 backbones, implemented on KittiSeg framework 2 [10], following Krinski et. al [11]; and the PoolNet 3 [12] with ResNet-50 backbone (a very recent network which achieved an impressive state of the art results in the SOD). The official code released by the authors of PoolNet was used in this work.…”

Section: Introductionmentioning

confidence: 99%

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

Ruíz

Krinski

Todt

2019

2019 19th International Conference on Advanced Robotics (ICAR)

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%