Search

Kushal Kafle Phones & Addresses

  • Sunnyvale, CA
  • Boston, MA
  • Rochester, NY

Publications

Us Patents

Extracting Attributes From Arbitrary Digital Images Utilizing A Multi-Attribute Contrastive Classification Neural Network

View page
US Patent:
20220383037, Dec 1, 2022
Filed:
May 27, 2021
Appl. No.:
17/332734
Inventors:
- San Jose CA, US
Kushal Kafle - Boston MA, US
Zhe Lin - Fremont CA, US
Zhihong Ding - Fremont CA, US
Scott Cohen - Sunnyvale CA, US
Quan Tran - San Jose CA, US
International Classification:
G06K 9/62
G06N 3/08
Abstract:
This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that extract multiple attributes from an object portrayed in a digital image utilizing a multi-attribute contrastive classification neural network. For example, the disclosed systems utilize a multi-attribute contrastive classification neural network that includes an embedding neural network, a localizer neural network, a multi-attention neural network, and a classifier neural network. In some cases, the disclosed systems train the multi-attribute contrastive classification neural network utilizing a multi-attribute, supervised-contrastive loss. In some embodiments, the disclosed systems generate negative attribute training labels for labeled digital images utilizing positive attribute labels that correspond to the labeled digital images.

Method For Training Parametric Machine Learning Systems

View page
US Patent:
20210027169, Jan 28, 2021
Filed:
Jul 24, 2020
Appl. No.:
16/938035
Inventors:
Christopher Kanan - Rochester NY, US
Tyler Hayes - West Henrietta NY, US
Kushal Kafle - Rochester NY, US
Robik Shrestha - Rochester NY, US
Assignee:
Rochester Institute of Technology - Rochester NY
International Classification:
G06N 3/08
G06N 3/04
Abstract:
A system and method for training a parametric machine learning system, include compressing a first data; storing the compressed first data; reconstructing a first selected amount of the stored compressed first data; providing a machine learning system; and training the machine learning system with the reconstructed first data and optionally raw data.
Kushal Kafle from Sunnyvale, CA Get Report