公开(公告)号：US11063915B1

公开(公告)日：2021-07-13

申请号：US15469363

申请日：2017-03-24

Applicant: Amazon Technologies, Inc.

Inventor： Frank Charles Paterra ,  Eric Neilsen ,  Elodie Wun ,  Mahadeva Navali Basavaraj ,  Shuo Yang ,  Vaibhav Tyagi ,  Xiao Li

IPC: H04L29/06 ,  G06F3/06 ,  H04L9/14 ,  H04L9/06 ,  H04L9/32 ,  H04L9/08

Abstract: A device such as a network-attachable data transfer device may be configured to operate in a cluster to coordinate the storage of data. A cluster manifest may include data and/or metadata related to devices of the cluster. In some cases, a cluster manifest may include, for each of one or more devices of a cluster: an encrypted payload; an identifier associated with the particular device; and an encrypted data entry. The encrypted payload may encode a cryptographic payload key used in part to perform storage operations. The encrypted data entry may include one or more encrypted partitions that are each decryptable by a different security module of the device. The decrypted partitions may be assembled to form a cryptographic key that may decrypt the encrypted payload. The cluster manifest may be provided to a locked device of a cluster as part of a process for unlocking the locked device.

公开(公告)号：US12182673B1

公开(公告)日：2024-12-31

申请号：US17315110

申请日：2021-05-07

Applicant: Amazon Technologies, Inc.

Inventor： Shuo Yang ,  Hao Zhou ,  Yuanjun Xiong ,  Wei Xia ,  Stefano Soatto

IPC: G06N3/04 ,  G06N20/00

Abstract: Machine learning models may be generated that are compatible with another machine learning model and satisfy a resource constraint. Techniques that ensure weight compatibility and architectural compatibility between a machine learning model being created to be compatible with another machine learning model are applied. The resource constraint is enforced so that the generated machine learning model also fits within the resource constraint.

公开(公告)号：US11475684B1

公开(公告)日：2022-10-18

申请号：US16830148

申请日：2020-03-25

Applicant: Amazon Technologies, Inc.

Inventor： Siqi Deng ,  Yuanjun Xiong ,  Wei Li ,  Shuo Yang ,  Wei Xia ,  Meng Wang

IPC: G06V30/32 ,  G06N3/08 ,  G06N3/04

Abstract: An image may be evaluated by a computer vision system to determine whether it is fit for analysis. The computer vision system may generate an embedding of the image. An embedding quality score (EQS) of the image may be determined based on the image's embedding and a reference embedding associated with a cluster of reference noisy images. The quality of the image may be evaluated based on the EQS of the image to determine whether the quality meets filter criteria. The image may be further processed when the quality is sufficient, or otherwise the image may be removed.

公开(公告)号：US11272164B1

公开(公告)日：2022-03-08

申请号：US16746313

申请日：2020-01-17

Applicant: Amazon Technologies, Inc.

Inventor： Yifan Xing ,  Yuanjun Xiong ,  Wei Xia ,  Wei Li ,  Shuo Yang ,  Meng Wang

IPC: H04N13/275 ,  G06T7/73 ,  G06N20/00 ,  G06T15/50

Abstract: Techniques for data synthesis for training datasets for machine learning applications are described. A first image of at least an object from a first viewpoint is obtained. The first image having associated first image metadata including a first location of a feature of the object in the first image. A model is generated from the first image, the model including a three-dimensional representation of the object. A second image is generated from the model, the second image including the object from a second viewpoint that is different from the first viewpoint. Second image metadata is generated, the second image metadata including a second location of the feature of the object in the second image, the second location corresponding to the first location adjusted for the difference between the second viewpoint and the first viewpoint.

公开(公告)号：US10706322B1

公开(公告)日：2020-07-07

申请号：US15821629

申请日：2017-11-22

Applicant: Amazon Technologies, Inc.

Inventor： Shuo Yang ,  Hao Wu ,  Jonathan Wu ,  Meng Wang

IPC: G06K9/34 ,  G06K9/62 ,  G06T7/70 ,  G06K9/72

Abstract: Embodiments of the present disclosure provide systems and processes for automatically determining a layout of text within an image that makes sense from a semantic perspective. In certain embodiments, the systems disclosed herein receive bounding box information relating to one or more bounding boxes that surround text within the image. The systems compare the received bounding box information to determine a clustering of bounding boxes that have an above threshold probability of including words that when read in order make sense semantically. For example, systems herein can determine whether words in a cluster correspond to a line of text.

公开(公告)号：US11216697B1

公开(公告)日：2022-01-04

申请号：US16815787

申请日：2020-03-11

Applicant: Amazon Technologies, Inc.

Inventor： Yantao Shen ,  Yuanjun Xiong ,  Siqi Deng ,  Wei Xia ,  Shuo Yang ,  Yifan Xing ,  Wei Li ,  Stefano Soatto

IPC: G06K9/62 ,  G06K9/00 ,  G06N20/00 ,  G06F16/538

Abstract: Techniques for building a backward compatible and backfill-free image search system are described. According to some embodiments, a backwards compatible training system trains a new embedding model to be backward compatible with the face embeddings (e.g., floating-point vectors) generated by a previous embedding model. In one embodiment, backwards compatible training uses a classifier of the previous embedding model as a form of constraint in the training of the new embedding model.