-
公开(公告)号：US12106541B2
公开(公告)日：2024-10-01
申请号：US17589709
申请日：2022-01-31
Applicant: Salesforce.com, Inc.
Inventor： Brian Chen , Ramprasaath Ramasamy Selvaraju , Juan Carlos Niebles Duque , Nikhil Naik
CPC classification number: G06V10/454 , G06V10/462 , G06V10/62
Abstract: Embodiments described herein provide an intelligent method to select instances, by utilizing unsupervised tracking for videos. Using this freely available form of supervision, a temporal constraint is adopted for selecting instances that ensures that different instances contain the same object while sampling the temporal augmentation from the video. In addition, using the information on the spatial extent of the tracked object, spatial constraints are applied to ensure that sampled instances overlap meaningfully with the tracked object. Taken together, these spatiotemporal constraints result in better supervisory signal for contrastive learning from videos.
-
公开(公告)号：US20220156592A1
公开(公告)日：2022-05-19
申请号：US17209013
申请日：2021-03-22
Applicant: salesforce.com, inc.
Inventor： Ramprasaath Ramasamy Selvaraju , Nikhil Naik
Abstract: Embodiments described herein embodiments described herein provide Contrastive Attention-Supervised Tuning (CAST), a training method to fix the visual grounding ability of contrastive SSL methods based on a data augmentation strategy using unsupervised saliency maps. In addition to the contrastive loss that encourages the model to pick the crop that comes from the corresponding image, CAST provides an explicit grounding supervision through a Grad-CAM based attention loss that enforces models to look at the specified object of interest that is common across different crops when making this decision. A new geometric transform is introduced for randomly cropping different views from an input image based on certain constraints derived from a saliency map.
-
公开(公告)号：US11508481B2
公开(公告)日：2022-11-22
申请号：US16895983
申请日：2020-06-08
Applicant: salesforce.com, inc.
Inventor： Nikhil Naik , Ali Madani , Nitish Shirish Keskar
Abstract: An analytics system uses one or more machine-learned models to predict a hormone receptor status from a H&E stain image. The system partitions H&E stain images each into a plurality of image tiles. Bags of tiles are created through sampling of the image tiles. The analytics system trains one or more machine-learned models with training H&E stain images having a positive or negative receptor status. The analytics system generates, via a tile featurization model, a tile feature vector for each image tile a test bag for a test H&E stain image. The analytics system generates, via an attention model, an aggregate feature vector for the test bag by aggregating the tile feature vectors of the test bag, wherein an attention weight is determined for each tile feature vector. The analytics system predicts a hormone receptor status by applying a prediction model to the aggregate feature vector for the test bag.
-
公开(公告)号：US20220156527A1
公开(公告)日：2022-05-19
申请号：US17209011
申请日：2021-03-22
Applicant: salesforce.com, inc.
Inventor： Ramprasaath Ramasamy Selvaraju , Nikhil Naik
Abstract: Embodiments described herein embodiments described herein provide Contrastive Attention-Supervised Tuning (CAST), a training method to fix the visual grounding ability of contrastive SSL methods based on a data augmentation strategy using unsupervised saliency maps. In addition to the contrastive loss that encourages the model to pick the crop that comes from the corresponding image, CAST provides an explicit grounding supervision through a Grad-CAM based attention loss that enforces models to look at the specified object of interest that is common across different crops when making this decision. A new geometric transform is introduced for randomly cropping different views from an input image based on certain constraints derived from a saliency map.
-
Patent Agency Ranking
公开(公告)号：US20210280311A1
公开(公告)日：2021-09-09
申请号：US16895983
申请日：2020-06-08
Applicant: salesforce.com, inc.
Inventor： Nikhil Naik , Ali Madani , Nitish Shirish Keskar
Abstract: An analytics system uses one or more machine-learned models to predict a hormone receptor status from a H&E stain image. The system partitions H&E stain images each into a plurality of image tiles. Bags of tiles are created through sampling of the image tiles. The analytics system trains one or more machine-learned models with training H&E stain images having a positive or negative receptor status. The analytics system generates, via a tile featurization model, a tile feature vector for each image tile a test bag for a test H&E stain image. The analytics system generates, via an attention model, an aggregate feature vector for the test bag by aggregating the tile feature vectors of the test bag, wherein an attention weight is determined for each tile feature vector. The analytics system predicts a hormone receptor status by applying a prediction model to the aggregate feature vector for the test bag.
-
公开(公告)号：US20210249105A1
公开(公告)日：2021-08-12
申请号：US17001045
申请日：2020-08-24
Applicant: salesforce.com, inc.
Inventor： Ali Madani , Bryan McCann , Nikhil Naik
Abstract: The present disclosure provides systems and methods for controllable protein generation. According to some embodiments, the systems and methods leverage neural network models and techniques that have been developed for other fields, in particular, natural language processing (NLP). In some embodiments, the systems and methods use or employ models implemented with transformer architectures developed for language modeling and apply the same to generative modeling for protein engineering.
-
公开(公告)号：US20210249100A1
公开(公告)日：2021-08-12
申请号：US17001068
申请日：2020-08-24
Applicant: salesforce.com, inc.
Inventor： Ali Madani , Bryan McCann , Nikhil Naik
Abstract: The present disclosure provides systems and methods for controllable protein generation. According to some embodiments, the systems and methods leverage neural network models and techniques that have been developed for other fields, in particular, natural language processing (NLP). In some embodiments, the systems and methods use or employ models implemented with transformer architectures developed for language modeling and apply the same to generative modeling for protein engineering.
-
公开(公告)号：US20230154139A1
公开(公告)日：2023-05-18
申请号：US17589709
申请日：2022-01-31
Applicant: salesforce.com, inc.
Inventor： Brian Chen , Ramprasaath Ramasamy Selvaraju , Juan Carlos Niebles Duque , Nikhil Naik
CPC classification number: G06V10/454 , G06V10/462 , G06V10/62
Abstract: Embodiments described herein provide an intelligent method to select instances, by utilizing unsupervised tracking for videos. Using this freely available form of supervision, a temporal constraint is adopted for selecting instances that ensures that different instances contain the same object while sampling the temporal augmentation from the video. In addition, using the information on the spatial extent of the tracked object, spatial constraints are applied to ensure that sampled instances overlap meaningfully with the tracked object. Taken together, these spatiotemporal constraints result in better supervisory signal for contrastive learning from videos.
-
公开(公告)号：US20210249104A1
公开(公告)日：2021-08-12
申请号：US17001090
申请日：2020-08-24
Applicant: salesforce.com, inc.
Inventor： Ali Madani , Bryan McCann , Nikhil Naik
Abstract: The present disclosure provides systems and methods for controllable protein generation. According to some embodiments, the systems and methods leverage neural network models and techniques that have been developed for other fields, in particular, natural language processing (NLP). In some embodiments, the systems and methods use or employ models implemented with transformer architectures developed for language modeling and apply the same to generative modeling for protein engineering.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.02 seconds)
