Merging Vision Transformers from Different Tasks and Domains
This work targets to merge various Vision Transformers (ViTs) trained on different tasks (ie,
datasets with different object categories) or domains (ie, datasets with the same categories …
datasets with different object categories) or domains (ie, datasets with the same categories …
Merging Vision Transformers from Different Tasks and Domains
P Ye, C Huang, M Shen, T Chen, Y Huang… - arXiv e …, 2023 - ui.adsabs.harvard.edu
This work targets to merge various Vision Transformers (ViTs) trained on different tasks (ie,
datasets with different object categories) or domains (ie, datasets with the same categories …
datasets with different object categories) or domains (ie, datasets with the same categories …