Views
No views yet
Pretrain vision transformers so that their patch representations transfer better to dense prediction (e.g., segmentation), without changing the pretraining objective.
1import timm
2model = timm.create_model("hf_hub:sinahmr/locatvit_base", pretrained=True)1@inproceedings{hajimiri2026locatvit,
2 author = {Hajimiri, Sina and Beizaee, Farzad and Shakeri, Fereshteh and Desrosiers, Christian and Ben Ayed, Ismail and Dolz, Jose},
3 title = {Locality-Attending Vision Transformer},
4 booktitle = {International Conference on Learning Representations},
5 year = {2026}
6}