SAK

These are checkpoints for our ICLR2025 paper: Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning.

Model Details

Model Description

• Developed by: Yuxiang Lu, Shengcao Cao, Yu-Xiong Wang
• License: mit

Model Sources

• Repository: https://github.com/innovator-zero/SAK
• Paper [OpenReview]: https://openreview.net/forum?id=eePww5u7J3
• Paper [arXiv]: https://arxiv.org/abs/2410.14633
• Project Page: https://innovator-zero.github.io/SAK/

Uses

Currently we directly provide checkpoints of pre-trained models in this repository. For detailed information on usage, please refer to our github repository.

Following are the checkpoint lists:

Stage 1

Teachers	Student backbone	Checkpoint
DINOv2-B, CLIP-B, SAM-B	ViT-S	BS_s1.pth
DINOv2-B, CLIP-B, SAM-B	ViT-B	BB_s1.pth
DINOv2-L, CLIP-L, SAM-L	ViT-B	LB_s1.pth
DINOv2-L, CLIP-L, SAM-L	ViT-L	LL_s1.pth

Stage 2

We provide two example checkpoints after Stage 2 training, initialized by BB_s1.pth from Stage 1 training:

• PASCAL-Context: BB_s2_pascal.pth
• NYUD-v2: BB_s2_nyud.pth

Citation

@inproceedings{lu2025swiss,
  title={Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning},
  author={Yuxiang Lu and Shengcao Cao and Yu-Xiong Wang},
  booktitle={The Thirteenth International Conference on Learning Representations},
  year={2025}
}