
提案されたT3DNet（Tiny 3D Network with augmEntation and disTillation）メソッドは、高い圧縮率を実現しながら、元のモデルと比較してわずかな精度低下で高性能を達成します。


coremsg

t3dnet-compressing-point-cloud-models-for-lightweight-3d-recognition


T3DNet: Compressing Point Cloud Models for Lightweight 3D Recognition



SlimSAM introduces a data-efficient compression method for SAM models, achieving superior performance with minimal training data.



SlimSAM: Data-Efficient Compression Method for SAM Models
