US 11,908,155 B2
Efficient pose estimation through iterative refinement
John Yang, Glendale, CA (US); Yash Sanjay Bhalgat, San Diego, CA (US); Fatih Murat Porikli, San Diego, CA (US); and Simyung Chang, Suwon (KR)
Assigned to QUALCOMM Incorporated, San Diego, CA (US)
Filed by QUALCOMM Incorporated, San Diego, CA (US)
Filed on Mar. 16, 2021, as Appl. No. 17/203,607.
Prior Publication US 2022/0301216 A1, Sep. 22, 2022
Int. Cl. G06F 18/213 (2023.01); G06N 20/00 (2019.01); G06T 7/70 (2017.01)
CPC G06T 7/70 (2017.01) [G06F 18/213 (2023.01); G06N 20/00 (2019.01); G06T 2207/20081 (2013.01)] 28 Claims
OG exemplary drawing
 
1. A method, comprising:
processing input data with a feature extraction stage of a machine learning model to generate a feature map;
applying an attention map to the feature map to generate an augmented feature map;
selecting a batch normalization layer, from a plurality of batch normalization layers, based on a loop count;
processing the augmented feature map with a refinement stage of the machine learning model to generate a refined feature map, wherein processing the augmented feature map with the refinement stage of the machine learning model comprises applying the batch normalization layer to the augmented feature map;
processing the refined feature map with a first regression stage of the machine learning model to generate multi-dimensional task output data; and
processing the refined feature map with an attention stage of the machine learning model to generate an updated attention map.