Automated Backend-Aware Post-Training Quantization

no code implementations • 27 Mar 2021 • Ziheng Jiang, Animesh Jain, Andrew Liu, Josh Fromm, Chengqian Ma, Tianqi Chen, Luis Ceze

Quantization is a key technique to reduce the resource requirement and improve the performance of neural network deployment.

Quantization

IA-MOT: Instance-Aware Multi-Object Tracking with Motion Consistency

no code implementations • 24 Jun 2020 • Jiarui Cai, Yizhou Wang, Haotian Zhang, Hung-Min Hsu, Chengqian Ma, Jenq-Neng Hwang

Meanwhile, the spatial attention, which focuses on the foreground within the bounding boxes, is generated from the given instance masks and applied to the extracted embedding features.

Multi-Object Tracking Multiple Object Tracking