Distill-then-prune: An Efficient Compression Framework for Real-time Stereo Matching Network on Edge Devices
원문 초록
In recent years, numerous real-time stereo matching methods have been introduced, but they often lack accuracy. These methods attempt to improve accuracy by introducing new modules or integrating traditional methods. However, the improvements are only modest. In this paper, we propose a novel strategy by incorporating knowledge distillation and model pruning to overcome the inherent trade-off between speed and accuracy. As a result, we obtained a model that maintains real-time performance while delivering high accuracy on edge devices. Our proposed method involves three key steps. Firstly, we review state-of-the-art methods and design our lightweight model by removing redundant modules from those efficient models through a comparison of their contributions. Next, we leverage the efficient model as the teacher to distill knowledge into the lightweight model. Finally, we systematically prune the lightweight model to obtain the final model. Through extensive experiments conducted on two widely-used benchmarks, Sceneflow and KITTI, we perform ablation studies to analyze the effectiveness of each module and present our state-of-the-art results.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Distilling Stereo Networks for Performant and Efficient Leaner Networks
ThermoStereoRT: Thermal Stereo Matching in Real Time via Knowledge Distillation and Attention-based Refinement
DVFL-Net: A Lightweight Distilled Video Focal Modulation Network for Spatio-Temporal Action Recognition
Learning Robust Stereo Matching in the Wild with Selective Mixture-of-Experts
The Trilemma of Truth in Large Language Models
ESMStereo: Enhanced ShuffleMixer Disparity Upsampling for Real-Time and Accurate Stereo Matching
토론
이 논문과 연결된 포럼 글이 아직 없습니다.