公开(公告)号：US20220405579A1

公开(公告)日：2022-12-22

申请号：US17613773

申请日：2021-03-03

Applicant: Google LLC

Inventor： Jiahui Yu ,  Pengchong Jin ,  Hanxiao Liu ,  Gabriel Mintzer Bender ,  Pieter-Jan Kindermans ,  Mingxing Tan ,  Xiaodan Song ,  Ruoming Pang ,  Quoc V. Le

IPC: G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting a neural network to perform a particular machine learning task while satisfying a set of constraints.

公开(公告)号：US20240378509A1

公开(公告)日：2024-11-14

申请号：US18784068

申请日：2024-07-25

Applicant: Google LLC

Inventor： Xianzhi Du ,  Yin Cui ,  Tsung-Yi Lin ,  Quoc V. Le ,  Pengchong Jin ,  Mingxing Tan ,  Golnaz Ghiasi ,  Xiaodan Song

IPC: G06N20/00 ,  G06F11/34 ,  G06N3/04

Abstract: A computer-implemented method of generating scale-permuted models can generate models having improved accuracy and reduced evaluation computational requirements. The method can include defining, by a computing system including one or more computing devices, a search space including a plurality of candidate permutations of a plurality of candidate feature blocks, each of the plurality of candidate feature blocks having a respective scale. The method can include performing, by the computing system, a plurality of search iterations by a search algorithm to select a scale-permuted model from the search space, the scale-permuted model based at least in part on a candidate permutation of the plurality of candidate permutations.

公开(公告)号：US12079695B2

公开(公告)日：2024-09-03

申请号：US17061355

申请日：2020-10-01

Applicant: Google LLC

Inventor： Xianzhi Du ,  Yin Cui ,  Tsung-Yi Lin ,  Quoc V. Le ,  Pengchong Jin ,  Mingxing Tan ,  Golnaz Ghiasi ,  Xiaodan Song

IPC: G06N20/00 ,  G06F11/34 ,  G06N3/04

CPC classification number: G06N20/00 ,  G06F11/3495 ,  G06N3/04

Abstract: A computer-implemented method of generating scale-permuted models can generate models having improved accuracy and reduced evaluation computational requirements. The method can include defining, by a computing system including one or more computing devices, a search space including a plurality of candidate permutations of a plurality of candidate feature blocks, each of the plurality of candidate feature blocks having a respective scale. The method can include performing, by the computing system, a plurality of search iterations by a search algorithm to select a scale-permuted model from the search space, the scale-permuted model based at least in part on a candidate permutation of the plurality of candidate permutations.

公开(公告)号：US20240022760A1

公开(公告)日：2024-01-18

申请号：US18256837

申请日：2021-08-05

Applicant: Google LLC

Inventor： Yinxiao Li ,  Peyman Milanfar ,  Feng Yang ,  Ce Liu ,  Ming-Hsuan Yang ,  Pengchong Jin

IPC: H04N19/59 ,  G06T3/00 ,  H04N19/117 ,  G06V10/74 ,  H04N19/503 ,  H04N19/70 ,  H04N19/80

CPC classification number: H04N19/59 ,  G06T3/0093 ,  H04N19/117 ,  G06V10/761 ,  H04N19/503 ,  H04N19/70 ,  H04N19/80

Abstract: Example aspects of the present disclosure are directed to systems and methods which feature a machine-learned video super-resolution (VSR) model which has been trained using a bi-directional training approach. In particular, the present disclosure provides a compression-informed (e.g., compression-aware) super-resolution model that can perform well on real-world videos with different levels of compression. Specifically, example models described herein can include three modules to robustly restore the missing information caused by video compression. First, a bi-directional recurrent module can be used to reduce the accumulated warping error from the random locations of the intra-frame from compressed video frames. Second, a detail-aware flow estimation module can be added to enable recovery of high resolution (HR) flow from compressed low resolution (LR) frames. Finally, a Laplacian enhancement module can add high-frequency information to the warped HR frames washed out by video encoding.

公开(公告)号：US20220108204A1

公开(公告)日：2022-04-07

申请号：US17061355

申请日：2020-10-01

Applicant: Google LLC

Inventor： Xianzhi Du ,  Yin Cui ,  Tsung-Yi Lin ,  Quoc V. Le ,  Pengchong Jin ,  Mingxing Tan ,  Golnaz Ghiasi ,  Xiaodan Song

IPC: G06N20/00 ,  G06N3/04 ,  G06F11/34

Abstract: A computer-implemented method of generating scale-permuted models can generate models having improved accuracy and reduced evaluation computational requirements. The method can include defining, by a computing system including one or more computing devices, a search space including a plurality of candidate permutations of a plurality of candidate feature blocks, each of the plurality of candidate feature blocks having a respective scale. The method can include performing, by the computing system, a plurality of search iterations by a search algorithm to select a scale-permuted model from the search space, the scale-permuted model based at least in part on a candidate permutation of the plurality of candidate permutations.