公开(公告)号：US20250131694A1

公开(公告)日：2025-04-24

申请号：US18688257

申请日：2021-09-09

Applicant: Google LLC

Inventor： Ahmet Iscen ,  Jack Louis Valmadre ,  Anurag Arnab ,  Cordelia Luise Schmid

IPC: G06V10/774 ,  G06V10/74 ,  G06V10/764 ,  G06V10/77 ,  G06V10/776 ,  G06V10/82 ,  G06V20/70

Abstract: Systems and methods for classification model training can use feature representation neighbors for mitigating label training overfitting. The systems and methods disclosed herein can utilize neighbor consistency regularization for training a classification model with and without noisy labels. The systems and methods can include a combined loss function with both a supervised learning loss and a neighbor consistency regularization loss.

公开(公告)号：US20240338387A1

公开(公告)日：2024-10-10

申请号：US18626268

申请日：2024-04-03

Applicant: Google LLC

Inventor： Ahmet Iscen ,  Alireza Fathi ,  Cordelia Luise Schmid

IPC: G06F16/28 ,  G06F16/242

CPC classification number: G06F16/285 ,  G06F16/2438

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing a classification task on a data item. In particular, a system classifies an input data item using key and value embeddings of memory data items.

公开(公告)号：US20240320493A1

公开(公告)日：2024-09-26

申请号：US18254634

申请日：2021-02-22

Applicant: Ahmet ISCEN ,  Andre Filgueiras de Araujo ,  Boqing Gong ,  Cordelia Luise SCHMID ,  Google LLC

Inventor： Ahmet Iscen ,  Andre Filgueiras de Araujo ,  Boqing Gong ,  Cordelia Luise Schmid

IPC: G06N3/084

CPC classification number: G06N3/084

Abstract: Class-balanced distillation can train recognition models with little to no bias even if the training dataset has a class imbalance. A two stage training process with instance sampling and class-balanced sampling can train the recognition model to recognize both head classes and tail classes. Moreover, one or more teacher classification models can be trained, and the knowledge can be distilled to a student classification model.