papers

Publications (6)

cs.LG2021

RCT: Resource Constrained Training for Edge AI

Tian Huang, Tao Luo, Ming Yan +2

Neural networks training on edge terminals is essential for edge AI computing, which needs to be adaptive to evolving environment. Quantised models can efficiently run on edge devi…

cs.NE2023

Efficient Spiking Neural Networks with Radix Encoding

Zhehui Wang, Xiaozhe Gu, Rick Goh +2

Spiking neural networks (SNNs) have advantages in latency and energy efficiency over traditional artificial neural networks (ANNs) due to its event-driven computation mechanism and…

cs.CV2022

CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow

Xiuchao Sui, Shaohua Li, Xue Geng +5

Optical flow estimation aims to find the 2D motion field by identifying corresponding pixels between two images. Despite the tremendous progress of deep learning-based optical flow…

eess.IV2021

Medical Image Segmentation Using Squeeze-and-Expansion Transformers

Shaohua Li, Xiuchao Sui, Xiangde Luo +3

Medical image segmentation is important for computer-aided diagnosis. Good segmentation demands the model to see the big picture and fine details simultaneously, i.e., to learn ima…

cs.CV2021

DTNN: Energy-efficient Inference with Dendrite Tree Inspired Neural Networks for Edge Vision Applications

Tao Luo, Wai Teng Tang, Matthew Kay Fei Lee +3

Deep neural networks (DNN) have achieved remarkable success in computer vision (CV). However, training and inference of DNN models are both memory and computation intensive, incurr…

quant-ph2022

Benchmarking Quantum(-inspired) Annealing Hardware on Practical Use Cases

Tian Huang, Jun Xu, Tao Luo +3

Quantum(-inspired) annealers show promise in solving combinatorial optimisation problems in practice. There has been extensive researches demonstrating the utility of D-Wave quantu…