Close
Metadata

@InProceedings{RuizKrinTodt:2020:ImDaAu,
               author = "Ruiz, Daniel Vitor and Krinski, Bruno Alexandre and Todt, 
                         Eduardo",
          affiliation = "{Federal Univesity of Paran{\'a}} and {Federal Univesity of 
                         Paran{\'a}} and {Federal Univesity of Paran{\'a}}",
                title = "IDA: Improved Data Augmentation Applied to Salient Object 
                         Detection",
            booktitle = "Proceedings...",
                 year = "2020",
               editor = "Musse, Soraia Raupp and Cesar Junior, Roberto Marcondes and 
                         Pelechano, Nuria and Wang, Zhangyang (Atlas)",
         organization = "Conference on Graphics, Patterns and Images, 33. (SIBGRAPI)",
            publisher = "IEEE Computer Society",
              address = "Los Alamitos",
             keywords = "data-augmentation, salient-object-detection, image-segmentation, 
                         deep-learning, image-inpainting.",
             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.",
  conference-location = "Virtual",
      conference-year = "Nov. 7-10, 2020",
             language = "en",
           targetfile = "PID6611905.pdf",
        urlaccessdate = "2021, Jan. 19"
}


Close