Knowledge Transferred Fine-Tuning: Convolutional Neural Network Is Born Again With Anti-Aliasing Even in Data-Limited Situations
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Access"
DOI: 10.1109/access.2022.3186101
Abstract: Anti-aliased convolutional neural networks (CNNs) are models that introduce blur filters to intermediate representations of CNNs to achieve high accuracy in image recognition tasks. A promising way to prepare a new anti-aliased CNN is to… read more here.
Keywords: loss; data limited; fine tuning; knowledge ... See more keywords
Efficient and Anti-Aliased Trimming for Rendering Large NURBS Models
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Transactions on Visualization and Computer Graphics"
DOI: 10.1109/tvcg.2018.2814987
Abstract: In Computer-Aided Design (CAD), Non-Uniform Rational B-Splines (NURBS) are a common model representation for export, simulation and visualization. In this paper, we present a direct rendering method for trimmed NURBS models based on their parametric… read more here.
Keywords: anti aliasing; nurbs models; anti aliased; trimming rendering ... See more keywords
Subpixel Deblurring of Anti‐Aliased Raster Clip‐Art
Sign Up to like & getrecommendations! Published in 2023 at "Computer Graphics Forum"
DOI: 10.1111/cgf.14744
Abstract: Artist generated clip‐art images typically consist of a small number of distinct, uniformly colored regions with clear boundaries. Legacy artist created images are often stored in low‐resolution (100x100px or less) anti‐aliased raster form. Compared to… read more here.
Keywords: topology; clip art; resolution; anti aliased ... See more keywords