-
公开(公告)号：US20190102651A1
公开(公告)日：2019-04-04
申请号：US16208518
申请日：2018-12-03
Applicant: Google LLC
Inventor： Yang Song , Jiang Wang , Charles J. Rosenberg
CPC classification number: G06K9/6215 , G06F16/51 , G06F16/5838 , G06K9/6212 , G06K9/627 , G06K9/66 , G06N3/0454 , G06N20/00
Abstract: Methods, systems, and apparatus, for determining fine-grained image similarity. In one aspect, a method includes training an image embedding function on image triplets by selecting image triplets of first, second and third images; generating, by the image embedding function, a first, second and third representations of the features of the first, second and third images; determining, based on the first representation of features and the second representation of features, a first similarity measure for the first image to the second image; determining, based on the first representation of features and the third representation of features, a second similarity measure for the the first image to the third image; determining, based on the first and second similarity measures, a performance measure of the image embedding function for the image triplet; and adjusting the parameter weights of the image embedding function based on the performance measures for the image triplets.
-
Patent Agency Ranking
公开(公告)号：US20210224660A1
公开(公告)日：2021-07-22
申请号：US16749570
申请日：2020-01-22
Applicant: Google LLC
Inventor： Yang Song , Raghav Gupta , Dengyong Zhou , Sanqiang Zhao
IPC: G06N3/08 , G06N3/04 , G06F40/284
Abstract: Provided is a knowledge distillation technique for training a student language model that, relative to a larger teacher language model, has a significantly smaller vocabulary, lower embedding dimensions, and/or hidden state dimensions. Specifically, aspects of the present disclosure are directed to a dual-training mechanism that trains the teacher and student language models simultaneously to obtain optimal word embeddings for the student vocabulary. In some implementations, this approach can be combined with learning shared projection matrices that transfer layer-wise knowledge from the teacher language model to the student language model. Example experimental results have also demonstrated higher compression efficiency and accuracy when compared with other state-of-the-art compression techniques, including the ability to compress the BERTBAsE model by more than 60×, with only a minor drop in downstream task metrics, resulting in a language model with a footprint of under 7 MB.
-
公开(公告)号：US10922350B2
公开(公告)日：2021-02-16
申请号：US16511522
申请日：2019-07-15
Applicant: Google LLC
Inventor： Ming Zhao , Yang Song , Hartwig Adam , Ullas Gargi , Yushi Jing , Henry Allan Rowley
IPC: G06F16/43 , G06F16/438 , G06F16/41 , G06F16/435 , G06F16/951 , G06F16/783 , G06K9/00 , G06F17/10 , G06K9/62
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for associating still images and videos. One method includes receiving a plurality of images and a plurality of videos and determining whether the images are related to the videos. The determining includes, for an image and a video, extracting features from the image and extracting features frames of the video, and comparing the features to determine whether the image is related to the video. The method further includes maintaining a data store storing data associating each image with each video determined to be related to the image.
-
公开(公告)号：US10339419B2
公开(公告)日：2019-07-02
申请号：US16208518
申请日：2018-12-03
Applicant: Google LLC
Inventor： Yang Song , Jiang Wang , Charles J. Rosenberg
Abstract: Methods, systems, and apparatus, for determining fine-grained image similarity. In one aspect, a method includes training an image embedding function on image triplets by selecting image triplets of first, second and third images; generating, by the image embedding function, a first, second and third representations of the features of the first, second and third images; determining, based on the first representation of features and the second representation of features, a first similarity measure for the first image to the second image; determining, based on the first representation of features and the third representation of features, a second similarity measure for the the first image to the third image; determining, based on the first and second similarity measures, a performance measure of the image embedding function for the image triplet; and adjusting the parameter weights of the image embedding function based on the performance measures for the image triplets.
-
公开(公告)号：US20190026268A1
公开(公告)日：2019-01-24
申请号：US16138606
申请日：2018-09-21
Applicant: Google LLC
Inventor： Ming Zhao , Yang Song , Hartwig Adam , Ullas Gargi , Yushi Jing , Henry Allan Rowley
CPC classification number: G06F16/438 , G06F16/41 , G06F16/435 , G06F16/7837 , G06F16/951 , G06F17/10 , G06K9/00751 , G06K9/629
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for associating still images and videos. One method includes receiving a plurality of images and a plurality of videos and determining whether the images are related to the videos. The determining includes, for an image and a video, extracting features from the image and extracting features frames of the video, and comparing the features to determine whether the image is related to the video. The method further includes maintaining a data store storing data associating each image with each video determined to be related to the image.
-
公开(公告)号：US10181091B2
公开(公告)日：2019-01-15
申请号：US15504870
申请日：2015-06-19
Applicant: Google LLC
Inventor： Yang Song , Jiang Wang , Charles J. Rosenberg
Abstract: Methods, systems, and apparatus, for determining fine-grained image similarity. In one aspect, a method includes training an image embedding function on image triplets by selecting image triplets of first, second and third images; generating, by the image embedding function, a first, second and third representations of the features of the first, second and third images; determining, based on the first representation of features and the second representation of features, a first similarity measure for the first image to the second image; determining, based on the first representation of features and the third representation of features, a second similarity measure for the first image to the third image; determining, based on the first and second similarity measures, a performance measure of the image embedding function for the image triplet; and adjusting the parameter weights of the image embedding function based on the performance measures for the image triplets.
-
-
-
-
-
Search Results
16
records
(took 0.027 seconds)
