Alpha-VL/ConvMAE
MCMAE is a masked autoencoder vision backbone combining convolutions with transformer architecture for image classification, detection, and segmentation.
Not currently ranked — collecting fresh signals.
star history
MCMAE (Masked Convolution Meets Masked Autoencoders) is a computer vision model that combines masked autoencoder pretraining with multi-scale convolutions. It provides pretrained backbone models that can be finetuned for downstream tasks including ImageNet classification, object detection (with Mask R-CNN), semantic segmentation, and video classification. The approach accelerates training and improves transfer learning performance compared to vanilla MAE by integrating hierarchical representations.
Frequently asked
- What is Alpha-VL/ConvMAE?
- MCMAE is a masked autoencoder vision backbone combining convolutions with transformer architecture for image classification, detection, and segmentation.
- Is ConvMAE open source?
- Yes — Alpha-VL/ConvMAE is open source, released under the MIT license.
- What language is ConvMAE written in?
- Alpha-VL/ConvMAE is primarily written in Python.
- How popular is ConvMAE?
- Alpha-VL/ConvMAE has 531 stars on GitHub.
- Where can I find ConvMAE?
- Alpha-VL/ConvMAE is on GitHub at https://github.com/Alpha-VL/ConvMAE.