Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training

von Yuan, Geng
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 25 of 50 (2023)

SPViT: Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning

von Kong, Zhenglun
Veröffentlicht in ECCV (17. : 2022 : Tel Aviv; Online) Computer vision – ECCV 2022 ; Part 11 (2022)

You Already Have It: A Generator-Free Low-Precision DNN Training Framework Using Stochastic Rounding

von Yuan, Geng
Veröffentlicht in ECCV (17. : 2022 : Tel Aviv; Online) Computer vision – ECCV 2022 ; Part 12 (2022)

MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge

von Yuan, Geng
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 25 of 36 (2022)