Zhuoran Xiong

Zhuoran Xiong

Auto-generated profile, based on publicly available information

Zhuoran Xiong

McGill University

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 June 2024 in Information Processing & Management
Verified
Journal Article
Closed access
YLYu Liu
Yu Liu
Duantengchuan LiDuantengchuan Li
Duantengchuan Li
KWKaili Wang
Kaili Wang
ZXZhuoran Xiong
Zhuoran Xiong
FSFobo Shi
Fobo Shi
BHBo Hang
Bo Hang

16 July 2024 in Information Processing & Management
Verified
Journal Article
Closed access
Duantengchuan LiDuantengchuan Li
Duantengchuan Li
YGYuxuan Gao
Yuxuan Gao
ZWZhihao Wang
Zhihao Wang
HQHua Qiu
Hua Qiu
PLPan Liu
Pan Liu
ZZZilong Zhang
Zilong Zhang

1 October 2026 in IEEE Embedded Systems Letters
Verified
Journal Article
Closed access
ZXZhuoran Xiong
Zhuoran Xiong
WGWarren J. Gross
Warren J. Gross
BMBrett H. Meyer
Brett H. Meyer
Enhancing the efficiency of deep neural networks enables complex computer vision applications, such as semantic segmentation, to meet latency requirements on resource-limited embedded systems. By optimizing network parameters, computation overhead can be reduced, leading to lower inference latency. We present TinySegAdapt, a zero-shot architecture search framework for deploying semantic segmentation networks on the ultra-low-power TinyML device. TinySegAdapt compresses networks through parameter-tuning-based architecture search, achieving 2.75 percentage points higher mIoU and 34.2% lower latency compared with filter pruning method. We perform accuracy measurement using a pretrained network and weight sharing, rather than accuracy proxies, yielding a 1.30 pp mIoU improvement. Moreover, TinySegAdapt accelerates the search process by 81.3% through evaluating models on a subset of the validation set without fine-tuning. TinySegAdapt finds competitive designs in just 36.5 hours to discover a variant that is 2.2× faster network on TinyML hardware with a 1.49 percentage point mIoU drop on the PASCAL VOC 2012 dataset.