ViLab-UCSD/MemSAC_ECCV2022
PyTorch code for MemSAC. To appear in ECCV 2022.
This project helps machine learning engineers and researchers adapt object recognition models to new, large datasets without needing extensive new labels. It takes existing labeled image data from one domain (e.g., real photos) and unlabeled images from a different, related domain (e.g., clip art or paintings) and produces a model that can accurately identify objects in the new domain. This is especially useful for tasks with many categories or fine-grained classes.
No commits in the last 6 months.
Use this if you need to deploy an object recognition model in a new visual environment where re-labeling thousands of images is impractical or too costly.
Not ideal if you have completely dissimilar image domains or if your dataset sizes are very small.
Stars
8
Forks
1
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Aug 08, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ViLab-UCSD/MemSAC_ECCV2022"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
BR-IDL/PaddleViT
:robot: PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+
pathak22/unsupervised-video
[CVPR 2017] Unsupervised deep learning using unlabelled videos on the web
IBM/CrossViT
Official implementation of CrossViT. https://arxiv.org/abs/2103.14899
NVlabs/GCVit
[ICML 2023] Official PyTorch implementation of Global Context Vision Transformers
ViTAE-Transformer/ViTDet
Unofficial implementation for [ECCV'22] "Exploring Plain Vision Transformer Backbones for Object...