@InProceedings{AbelloJr:2019:OpSuRe,
               author = "Abello, Antonio Augusto and Jr, Roberto Hirata",
          affiliation = "University of S{\~a}o Paulo, Brazil and University of S{\~a}o 
                         Paulo, Brazil",
                title = "Optimizing Super Resolution for Face Recognition",
            booktitle = "Proceedings...",
                 year = "2019",
               editor = "Oliveira, Luciano Rebou{\c{c}}as de and Sarder, Pinaki and Lage, 
                         Marcos and Sadlo, Filip",
         organization = "Conference on Graphics, Patterns and Images, 32. (SIBGRAPI)",
            publisher = "IEEE Computer Society",
              address = "Los Alamitos",
             keywords = "deep learning, super-resolution, face-recognition.",
             abstract = "Face Super-Resolution is a subset of Super Resolution (SR) that 
                         aims to retrieve a high-resolution (HR) image of a face from a 
                         lower resolution input. Recently, Deep Learning (DL) methods have 
                         improved drastically the quality of SR generated images. However, 
                         these qualitative improvements are not always followed by 
                         quantitative improvements in the traditional metrics of the area, 
                         namely PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural 
                         Similarity Index). In some cases, models that perform better in 
                         opinion scores and qualitative evaluation have worse performance 
                         in these metrics, indicating they are not sufficiently 
                         informative. To address this issue we propose a task-based 
                         evaluation procedure based on the comparative performance of face 
                         recognition algorithms on HR and SR images to evaluate how well 
                         the models retrieve high-frequency and identity defining 
                         information. Furthermore, as our face recognition model is 
                         differentiable, this leads to a novel loss function that can be 
                         optimized to improve performance in these tasks. We successfully 
                         apply our evaluation method to validate this training method, 
                         yielding promising results.",
  conference-location = "Rio de Janeiro, RJ, Brazil",
      conference-year = "28-31 Oct. 2019",
                  doi = "10.1109/SIBGRAPI.2019.00034",
                  url = "http://dx.doi.org/10.1109/SIBGRAPI.2019.00034",
             language = "en",
                  ibi = "8JMKD3MGPEW34M/3U2JUJH",
                  url = "http://urlib.net/ibi/8JMKD3MGPEW34M/3U2JUJH",
           targetfile = "camera-ready.pdf",
        urlaccessdate = "2024, Apr. 28"
}