arXiv · 2023 · Preprint

An Efficient General-Purpose Modular Vision Model via Multi-Task Heterogeneous Training

Z. Chen, Mingyu Ding, Yikang Shen, Wei Zhan, M. Tomizuka, E. Learned-Miller, Chuang Gan

Date: 2023-06-29
Citations: 9
arXiv: 2306.17165 ↗

Cite

@misc{chen2023efficient,
  title = {An Efficient General-Purpose Modular Vision Model via Multi-Task Heterogeneous Training},
  author = {Z. Chen and Mingyu Ding and Yikang Shen and Wei Zhan and M. Tomizuka and E. Learned-Miller and Chuang Gan},
  year = {2023},
  eprint = {2306.17165},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2306.17165},
}