Jie Ran — accepted AI-conference papers

2024

Hundred-Kilobyte Lookup Tables for Efficient Single-Image Super-Resolution

Binxiao Huang, Jason Chun Lok Li, Jie Ran, Boyu Li, Jiajun Zhou, Dahai Yu +1

IJCAI 2024poster

Conventional super-resolution (SR) schemes make heavy use of convolutional neural networks (CNNs), which involve intensive multiply-accumulate (MAC) operations, and require specialized hardware such as graphics processing units. This contradicts the regime of edge AI that often runs on devices strai…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗

2021

Deformable Butterfly: A Highly Structured and Sparse Linear Transform

Rui Lin, Jie Ran, King Hung Chiu, Graziano Chesi, Ngai Wong

NeurIPS 2021poster

We introduce a new kind of linear transform named Deformable Butterfly (DeBut) that generalizes the conventional butterfly matrices and can be adapted to various input-output dimensions. It inherits the fine-to-coarse-grained learnable hierarchy of traditional butterflies and when deployed to neural…

Cited by 21 Source ↗PDF ↗code ↗Scholar ↗