DONUT-hole: DONUT Sparsification by Harnessing Knowledge and Optimizing Learning Efficiency

9 November 2023

Papers citing "DONUT-hole: DONUT Sparsification by Harnessing Knowledge and Optimizing Learning Efficiency"

3 / 3 papers shown

Title
TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation R. Liu Kailun Yang Alina Roitberg Jiaming Zhang Kunyu Peng Huayao Liu Yaonan Wang Rainer Stiefelhagen ViT 34 36 0 27 Feb 2022
Distilling Knowledge via Knowledge Review Pengguang Chen Shu-Lin Liu Hengshuang Zhao Jiaya Jia 147 416 0 19 Apr 2021
LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding Yang Xu Yiheng Xu Tengchao Lv Lei Cui Furu Wei ... D. Florêncio Cha Zhang Wanxiang Che Min Zhang Lidong Zhou ViT MLLM 145 498 0 29 Dec 2020