公开(公告)号：US20240203532A1

公开(公告)日：2024-06-20

申请号：US18589215

申请日：2024-02-27

Applicant: Salesforce, Inc.

Inventor： Ali Madani ,  Bryan McCann ,  Nikhil Naik

IPC: G16B40/30 ,  G06F30/20 ,  G06F111/08 ,  G16B5/20 ,  G16B15/20 ,  G16B25/10 ,  G16B30/00 ,  G16B40/20 ,  G16B50/10

CPC classification number: G16B40/30 ,  G06F30/20 ,  G16B5/20 ,  G16B15/20 ,  G16B25/10 ,  G16B30/00 ,  G16B40/20 ,  G16B50/10 ,  G06F2111/08

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：US20240161248A1

公开(公告)日：2024-05-16

申请号：US18175156

申请日：2023-02-27

Applicant: Salesforce Inc.

Inventor： Nikhil Naik ,  Bram Wallace

IPC: G06T5/00 ,  G06T5/30 ,  G06T5/50

CPC classification number: G06T5/002 ,  G06T5/30 ,  G06T5/50 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20216

Abstract: Embodiments described herein provide systems and methods for image editing. a first copy and a second copy of an input image are generated; noise is iteratively added to the first copy and the second copy by: updating the first copy based on a first inverted output of a denoising diffusion model (DDM) based on the second copy and a first caption and updating the second copy based on a second inverted output of the DDM based on the first copy and the first caption. A resultant noised image is iteratively denoised by a reverse process using the DDM conditioned on a second caption, thereby producing a final image.

公开(公告)号：US11941086B2

公开(公告)日：2024-03-26

申请号：US17209011

申请日：2021-03-22

Applicant: Salesforce, Inc.

Inventor： Ramprasaath Ramasamy Selvaraju ,  Nikhil Naik

IPC: G06F18/21 ,  G06F17/16 ,  G06F18/214 ,  G06N3/045 ,  G06N3/084 ,  G06N3/10 ,  G06T7/194 ,  G06V10/25 ,  G06V10/46

CPC classification number: G06F18/2193 ,  G06F17/16 ,  G06F18/214 ,  G06N3/045 ,  G06N3/084 ,  G06N3/10 ,  G06T7/194 ,  G06V10/25 ,  G06V10/462 ,  G06T2207/20084

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：US11948665B2

公开(公告)日：2024-04-02

申请号：US17001068

申请日：2020-08-24

Applicant: Salesforce, Inc.

Inventor： Ali Madani ,  Bryan McCann ,  Nikhil Naik

IPC: G16B40/30 ,  G06F30/20 ,  G06F111/08 ,  G16B5/20 ,  G16B15/20 ,  G16B25/10 ,  G16B30/00 ,  G16B40/20 ,  G16B50/10

CPC classification number: G16B40/30 ,  G06F30/20 ,  G16B5/20 ,  G16B15/20 ,  G16B25/10 ,  G16B30/00 ,  G16B40/20 ,  G16B50/10 ,  G06F2111/08

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：US20230042318A1

公开(公告)日：2023-02-09

申请号：US17971312

申请日：2022-10-21

Applicant: Salesforce, Inc.

Inventor： Nikhil Naik ,  Ali Madani ,  Nitish Shirish Keskar

IPC: G16H50/20 ,  G06K9/62 ,  G06N5/04 ,  G16H10/20 ,  G06N20/00

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 non-overlapping image tiles. Bags of tiles are created through sampling of the image tiles. For each H&E stain image, the system generates a feature vector from a bag of tiles sampled from the partitioned 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. With the trained models, the analytics system predicts a hormone receptor status by applying a prediction model to the feature vector for a test H&E stain image.

公开(公告)号：US20240386685A1

公开(公告)日：2024-11-21

申请号：US18538825

申请日：2023-12-13

Applicant: Salesforce, Inc.

Inventor： Senthil Purushwalkam Shiva Prakash ,  Nikhil Naik

IPC: G06T19/20 ,  G06T7/194 ,  G06T7/50 ,  H04N13/279

Abstract: Embodiments described herein provide a 3D generation system from a single RGB image of an object by inferring the hidden 3D structure of objects based on 2D priors learnt by a generative model. Specifically, the 3D generation system may reconstruct the 3D structure of an object from an input of a single RGB image and optionally an associated depth estimate. For example, a radiance field is formulated to depict the input image in one viewpoint of the target 3D object, based on which other viewpoints of the 3D object can be inferred. Based on the visible surface depicted by the input image, points between the reference camera and the surface are assigned with zero density, and points on the surface are assigned with high density and color equal to the corresponding pixel in the input image.

公开(公告)号：US20240303873A1

公开(公告)日：2024-09-12

申请号：US18333695

申请日：2023-06-13

Applicant: Salesforce, Inc.

Inventor： Bram Wallace ,  Nikhil Naik

IPC: G06T11/00 ,  G06T5/00

CPC classification number: G06T11/00 ,  G06T5/70 ,  G06T2207/20084

Abstract: Embodiments described herein provide a method of generating an image. the method comprises receiving, via a data interface, a natural language prompt, obtaining a noised image vector, and generating a denoised image vector by a first forward pass of a plurality of iterations of a denoising diffusion model with the noised image vector as an input and conditioned on the natural language prompt. The method further includes calculating a gradient of a loss function based on the denoised image vector with respect to the noised image vector, and updating the noised image vector based on the gradient. A final image is generated using a final forward pass of the denoising diffusion model with the updated noised image vector as an input and conditioned on the natural language prompt.

公开(公告)号：US11810298B2

公开(公告)日：2023-11-07

申请号：US17971312

申请日：2022-10-21

Applicant: Salesforce, Inc.

Inventor： Nikhil Naik ,  Ali Madani ,  Nitish Shirish Keskar

IPC: G06T7/00 ,  G16H50/20 ,  G06N5/04 ,  G16H10/20 ,  G06N20/00 ,  G06F18/21 ,  G06F18/214 ,  G06V20/69

CPC classification number: G06T7/0012 ,  G06F18/217 ,  G06F18/2148 ,  G06N5/04 ,  G06N20/00 ,  G06V20/69 ,  G16H10/20 ,  G16H50/20 ,  G06V2201/03

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 non-overlapping image tiles. Bags of tiles are created through sampling of the image tiles. For each H&E stain image, the system generates a feature vector from a bag of tiles sampled from the partitioned 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. With the trained models, the analytics system predicts a hormone receptor status by applying a prediction model to the feature vector for a test H&E stain image.

公开(公告)号：US20240386653A1

公开(公告)日：2024-11-21

申请号：US18538814

申请日：2023-12-13

Applicant: Salesforce, Inc.

Inventor： Senthil Purushwalkam Shiva Prakash ,  Nikhil Naik

IPC: G06T15/20 ,  G06T7/50 ,  G06T15/06 ,  G06T19/20

Abstract: Embodiments described herein provide a 3D generation system from a single RGB image of an object by inferring the hidden 3D structure of objects based on 2D priors learnt by a generative model. Specifically, the 3D generation system may reconstruct the 3D structure of an object from an input of a single RGB image and optionally an associated depth estimate. For example, a radiance field is formulated to depict the input image in one viewpoint of the target 3D object, based on which other viewpoints of the 3D object can be inferred. Based on the visible surface depicted by the input image, points between the reference camera and the surface are assigned with zero density, and points on the surface are assigned with high density and color equal to the corresponding pixel in the input image.