BezierFormer: A Unified Architecture for 2D and 3D Lane Detection

no code implementations • 25 Apr 2024 • Zhiwei Dong, Xi Zhu, Xiya Cao, Ran Ding, Wei Li, Caifa Zhou, Yongliang Wang, Qiangbo Liu

B\'{e}zierFormer formulate queries as B\'{e}zier control points and incorporate a novel B\'{e}zier curve attention mechanism.

QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models

2 code implementations • 12 Oct 2023 • Jing Liu, Ruihao Gong, Xiuying Wei, Zhiwei Dong, Jianfei Cai, Bohan Zhuang

Additionally, an adaptive strategy is designed to autonomously determine the optimal number of sub-channels for channel disassembly.

Quantization

NeMO: Neural Map Growing System for Spatiotemporal Fusion in Bird's-Eye-View and BDD-Map Benchmark

no code implementations • 7 Jun 2023 • Xi Zhu, Xiya Cao, Zhiwei Dong, Caifa Zhou, Qiangbo Liu, Wei Li, Yongliang Wang

We also provide a new scene-level BEV map evaluation setting along with the corresponding baseline for a more comprehensive comparison.

Autonomous Driving Time Series

CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection

2 code implementations • CVPR 2020 • Zhiwei Dong, Guoxuan Li, Yue Liao, Fei Wang, Pengju Ren, Chen Qian

CentripetalNet predicts the position and the centripetal shift of the corner points and matches corners whose shifted results are aligned.

Instance Segmentation object-detection +4