CVPR 2023 AVA: Accessibility, Vision, and Autonomy Meet Challenge Submission
This is my code to train AVA-02 models on the CVPR 2023 AVA Instance Segmentation Challenge. I got an overall mAP of 52.68% The relevant files are in the EVA-02/det folder. Specifically:
- XWorld Dataset config: link
- XWorld Loader link
- Training configs link the rest of the files belong to BAAI Vision Team! BAAI Vision Feel free to email me in case of anything: akiruga [at] udel [dot] edu
EVA: Visual Representation Fantasies from BAAI
-
EVA-01 (CVPR 2023,
๐ highlight๐ ) - Exploring the Limits of Masked Visual Representation Learning at Scale -
EVA-02 (Arxiv 2023) - A Visual Representation for Neon Genesis
-
EVA-CLIP (Arxiv 2023) - Improved Training Techniques for CLIP at Scale
Contact
- We are hiring at all levels at BAAI Vision Team, including full-time researchers, engineers and interns.
If you are interested in working with us on foundation model, self-supervised learning and multimodal learning, please contact Yue Cao (
caoyue@baai.ac.cn
) and Xinlong Wang (wangxinlong@baai.ac.cn
).
License
The content of this project itself is licensed under LICENSE.