公开(公告)号：US10909728B1

公开(公告)日：2021-02-02

申请号：US16400900

申请日：2019-05-01

Applicant: Amazon Technologies, Inc.

Inventor： Srikar Appalaraju ,  R. Manmatha ,  Yash Patel

IPC: G06T9/00 ,  G06N20/10 ,  G06N3/08 ,  G06T3/40

Abstract: Techniques for learned lossy image compression are described. A system may perform image compression using an image compression model that includes an encoder to compress an image and a decoder to reconstruct the image. The encoder and the decoder are trained using machine learning techniques. After training, the encoder can encode image data to generate compressed image data and the decoder can decode compressed image data to generate reconstructed image data.

公开(公告)号：US10984560B1

公开(公告)日：2021-04-20

申请号：US16370598

申请日：2019-03-29

Applicant: Amazon Technologies, Inc.

Inventor： Srikar Appalaraju ,  R. Manmatha ,  Tal Hassner

IPC: G06N3/04 ,  G06T9/00 ,  G06K9/00 ,  G06K9/62

Abstract: Techniques for performing learnt image compression and object detection using compressed image data are described. A system may perform image compression using an image compression model that includes an encoder, an entropy model, and a decoder. The encoder, the entropy model, and the decoder may be jointly trained using machine learning based on training data. After training, the encoder and the decoder may be separated to encode image data to generate compressed image data or to decode compressed image data to generate reconstructed image data. In addition, the system may perform object detection using a compressed object detection model that processes compressed image data generated by the image compression model. For example, the compressed object detection model may perform partial decoding using a single layer of the decoder and perform compressed object detection on the partially decoded image data.

公开(公告)号：US10965948B1

公开(公告)日：2021-03-30

申请号：US16713910

申请日：2019-12-13

Applicant: Amazon Technologies, Inc.

Inventor： Srikar Appalaraju ,  Yash Patel ,  R. Manmatha

IPC: H04N19/20 ,  H04N19/91 ,  H04N19/33 ,  G06T9/00

Abstract: The present application relates to a multi-stage encoder/decoder system that provides image compression using hierarchical auto-regressive models and saliency-based masks. The multi-stage encoder/decoder system includes a first stage and a second stage of a trained image compression network, such that the second stage, based on the image compression performed by the first stage, identify certain redundancies that can be removed from the bit string to reduce the storage and bandwidth requirements. Additionally, by using saliency-based masks, distortions in different sections of the image can be weighted differently to further improve the image compression performance.