search

czczup / ViT-Adapter

[ICLR 2023 Spotlight] Vision Transformer Adapter for Dense Predictions
https://arxiv.org/abs/2205.08534
Apache License 2.0
1.27k stars 140 forks source link

Wanted to know if there is an MAE based implementation for Vit Adapter ? #181

Open ayushnangia opened 3 months ago

ayushnangia commented 3 months ago
  1. Request: Implement a Masked Autoencoder (MAE) based version of ViT-Adapter for segmentation tasks.
  2. Rationale: Leverage MAE's self-supervised learning capabilities to potentially improve segmentation performance.
  3. Query: Has there been any consideration or work on integrating MAE with ViT-Adapter for segmentation?