公开(公告)号：US20240428605A1

公开(公告)日：2024-12-26

申请号：US18214108

申请日：2023-06-26

Applicant: Amazon Technologies, Inc.

Inventor： Kun Li ,  Pragyana K. Mishra

IPC: G06V30/19 ,  G06V20/62 ,  G06V20/70 ,  G06V30/14 ,  G06V30/148 ,  G06V30/30

Abstract: Devices and techniques are generally described for privacy preservation for computer vision models. In some examples, a first field of text and a second field of text may be detected in a first image. A first alpha-numeric text string may be detected in the first field and a second alpha-numeric text string may be detected in the second field. A first sub-image including the first alpha-numeric text string may be generated and a second sub-image including the second alpha-numeric text string may be generated. The first sub-image may be sent to a first computing device for annotation and the second sub-image may be sent to a second computing device for annotation.

公开(公告)号：US12008788B1

公开(公告)日：2024-06-11

申请号：US17501555

申请日：2021-10-14

Applicant: Amazon Technologies, Inc.

Inventor： Kun Li ,  Pragyana K. Mishra

IPC: G06T7/73 ,  G06N3/04 ,  G06N3/08 ,  G06N20/10 ,  G06T7/33

CPC classification number: G06T7/74 ,  G06N3/04 ,  G06N3/08 ,  G06N20/10 ,  G06T7/337

Abstract: Techniques for detection of spatial relationships are provided. An input image is divided into a set of patches, and a first feature tensor is generated for a first patch of the set of patches. The first feature tensor is processed using an attention mechanism to generate a first transformed feature tensor, and a classification indicating distancing between physical entities in the input image is generated based at least in part on the first transformed feature tensor.

公开(公告)号：US11568176B1

公开(公告)日：2023-01-31

申请号：US17358316

申请日：2021-06-25

Applicant: Amazon Technologies, Inc.

Inventor： Kun Li ,  Pragyana K. Mishra

IPC: G06K9/62 ,  G06V30/194

Abstract: Deep feature extraction and training tools and processes may facilitate extraction and understanding of deep features utilized by deep learning models. For example, imaging data may be tessellated and masked to generate a plurality of masked images. The masked images may be processed by a deep learning model to generate a plurality of masked outputs. The masked outputs may be aggregated for each cell of the tessellated image and compared to an original output for the imaging data from the deep learning model. Individual cells and associated image regions having masked outputs that correspond to the original output may comprise deep features utilized by the deep learning model.