Patents by Inventor Evan Shelhamer

Evan Shelhamer has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 11763545
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for efficiently, quickly, and flexibly generating and providing pixel-wise classification predictions utilizing early exit heads of a multi-exit pixel-level prediction neural network. For example, the disclosed systems utilize a multi-exit pixel-level prediction neural network to generate classification predictions for a digital image on the pixel level. The multi-exit pixel-level prediction neural network includes a specialized architecture with early exit heads having unique encoder-decoder architectures for generating pixel-wise classification predictions at different early exit stages. In some embodiments, the disclosed systems implement a spatial confidence-adaptive scheme to mask certain predicted pixels to prevent further processing of the masked pixels and thereby reduce computation.
    Type: Grant
    Filed: March 26, 2021
    Date of Patent: September 19, 2023
    Assignee: Adobe Inc.
    Inventors: Evan Shelhamer, Zhuang Liu
  • Publication number: 20220309285
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for efficiently, quickly, and flexibly generating and providing pixel-wise classification predictions utilizing early exit heads of a multi-exit pixel-level prediction neural network. For example, the disclosed systems utilize a multi-exit pixel-level prediction neural network to generate classification predictions for a digital image on the pixel level. The multi-exit pixel-level prediction neural network includes a specialized architecture with early exit heads having unique encoder-decoder architectures for generating pixel-wise classification predictions at different early exit stages. In some embodiments, the disclosed systems implement a spatial confidence-adaptive scheme to mask certain predicted pixels to prevent further processing of the masked pixels and thereby reduce computation.
    Type: Application
    Filed: March 26, 2021
    Publication date: September 29, 2022
    Inventors: Evan Shelhamer, Zhuang Liu