-
公开(公告)号：US20220300761A1
公开(公告)日：2022-09-22
申请号：US17328779
申请日：2021-05-24
Applicant: salesforce.com, inc.
Inventor： Shu Zhang , Chetan Ramaiah , Caiming Xiong , Ran Xu
Abstract: Embodiments described herein provide a hierarchical multi-label framework to learn an embedding function that may capture the hierarchical relationship between classes at different levels in the hierarchy. Specifically, supervised contrastive learning framework may be extended to the hierarchical multi-label setting. Each data point has multiple dependent labels, and the relationship between labels is represented as a hierarchy of labels. The relationship between the different levels of labels may then be learnt by a contrastive learning framework.
-
公开(公告)号：US20210334666A1
公开(公告)日：2021-10-28
申请号：US16854913
申请日：2020-04-22
Applicant: salesforce.com, inc.
Inventor： Jessica Lundin , Owen Winne Schoppe , Alan Martin Ross , Brian J. Lonsdorf , David James Woodward , Sönke Rohde , Michael Reynolds Sollami , Chetan Ramaiah
IPC: G06N5/02 , G06N20/00 , G06F40/109 , G06F17/16
Abstract: A textual properties model is used to infer values for certain font properties of interest given certain text-related data, such as rendered text images. The model may be used for numerous purposes, such as aiding with document layout, identifying font families that are similar to a given font families, and generating new font families with specific desired properties. In some embodiments, the model is trained from a combination of synthetic data that is labeled with values for the font properties of interest, and partially-labeled data from existing “real-world” documents.
-
公开(公告)号：US11669745B2
公开(公告)日：2023-06-06
申请号：US17080276
申请日：2020-10-26
Applicant: salesforce.com, inc.
Inventor： Chetan Ramaiah , Peng Tang , Caiming Xiong
IPC: G06F18/21 , G06N3/082 , G06F18/214
CPC classification number: G06F18/2178 , G06F18/2155 , G06N3/082
Abstract: A method for generating a neural network for detecting one or more objects in images includes generating one or more self-supervised proposal learning losses based on the one or more proposal features and corresponding proposal feature predictions. One or more consistency-based proposal learning losses are generated based on noisy proposal feature predictions and the corresponding proposal predictions without noise. A combined loss is generated using the one or more self-supervised proposal learning losses and one or more consistency-based proposal learning losses. The neural network is updated based on the combined loss.
-
Patent Agency Ranking
公开(公告)号：US20230162490A1
公开(公告)日：2023-05-25
申请号：US17589725
申请日：2022-01-31
Applicant: salesforce.com, inc.
Inventor： Shu Zhang , Junnan Li , Ran Xu , Caiming Xiong , Chetan Ramaiah
IPC: G06V10/776 , G06V10/74 , G06F40/284 , G06F40/166 , G06F40/126 , G06V10/80 , G06F16/583 , G06F16/56
CPC classification number: G06V10/776 , G06V10/761 , G06F40/284 , G06F40/166 , G06F40/126 , G06V10/806 , G06F16/5846 , G06F16/56
Abstract: Embodiments described herein a CROss-Modal Distribution Alignment (CROMDA) model for vision-language pretraining, which can be used for retrieval downstream tasks. In the CROMDA mode, global cross-modal representations are aligned on each unimodality. Specifically, a uni-modal global similarity between an image/text and the image/text feature queue are computed. A softmax-normalized distribution is then generated based on the computed similarity. The distribution thus takes advantage of property of the global structure of the queue. CROMDA then aligns the two distributions and learns a modal invariant global representation. In this way, CROMDA is able to obtain invariant property in each modality, where images with similar text representations should be similar and vice versa.
-
公开(公告)号：US20230153307A1
公开(公告)日：2023-05-18
申请号：US17588022
申请日：2022-01-28
Applicant: salesforce.com, inc.
Inventor： Luyu Yang , Mingfei Gao , Zeyuan Chen , Ran Xu , Chetan Ramaiah
IPC: G06F16/2455 , G06F16/242 , G06N20/00
CPC classification number: G06F16/24568 , G06F16/2425 , G06N20/00
Abstract: Embodiments described herein provide an online domain adaptation framework based on cross-domain bootstrapping for online domain adaptation, in which the target domain streaming data is deleted immediately after adapted. At each online query, the data diversity is increased across domains by bootstrapping the source domain to form diverse combinations with the current target query. To fully take advantage of the valuable discrepancies among the diverse combinations, a set of independent learners are trained to preserve the differences. The knowledge of the learners is then integrated by exchanging their predicted pseudo-labels on the current target query to co-supervise the learning on the target domain, but without sharing the weights to maintain the learners' divergence.
-
公开(公告)号：US11610138B2
公开(公告)日：2023-03-21
申请号：US16854913
申请日：2020-04-22
Applicant: salesforce.com, inc.
Inventor： Jessica Lundin , Owen Winne Schoppe , Alan Martin Ross , Brian J. Lonsdorf , David James Woodward , Sönke Rohde , Michael Reynolds Sollami , Chetan Ramaiah
IPC: G06V30/244 , G06N5/02 , G06F17/16 , G06F40/109 , G06N20/00 , G06N5/04 , G06T7/00
Abstract: A textual properties model is used to infer values for certain font properties of interest given certain text-related data, such as rendered text images. The model may be used for numerous purposes, such as aiding with document layout, identifying font families that are similar to a given font families, and generating new font families with specific desired properties. In some embodiments, the model is trained from a combination of synthetic data that is labeled with values for the font properties of interest, and partially-labeled data from existing “real-world” documents.
-
公开(公告)号：US11495011B2
公开(公告)日：2022-11-08
申请号：US16988536
申请日：2020-08-07
Applicant: salesforce.com, inc.
Inventor： Shu Zhang , Chetan Ramaiah , Ran Xu , Caiming Xiong
Abstract: The system has a form analysis module that receives an image of a form into which values have been filled for the possible fields of information on the form, such as first name, address, age, and the like. By using a library of form templates, a form analysis module allows both flexibility of form processing and simplicity for the user. That is, the techniques used by the form analysis module allow the processing of any form image for which the library has a form template example. The form image need not precisely match any form template, but rather may be scaled or shifted relative to a corresponding template. Additionally, the user need only provide the form image itself, without providing any additional exemplars, metadata for training, or the like.
-
公开(公告)号：US20210216828A1
公开(公告)日：2021-07-15
申请号：US17080276
申请日：2020-10-26
Applicant: salesforce.com, inc.
Inventor： Chetan Ramaiah , Peng Tang , Caiming Xiong
Abstract: A method for generating a neural network for detecting one or more objects in images includes generating one or more self-supervised proposal learning losses based on the one or more proposal features and corresponding proposal feature predictions. One or more consistency-based proposal learning losses are generated based on noisy proposal feature predictions and the corresponding proposal predictions without noise. A combined loss is generated using the one or more self-supervised proposal learning losses and one or more consistency-based proposal learning losses. The neural network is updated based on the combined loss.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.015 seconds)
