KentoNishi/JTR-CVPR-2024
[CVPR 2024] Joint-Task Regularization for Partially Labeled Multi-Task Learning
This project helps machine learning researchers improve the accuracy of models that perform several computer vision tasks simultaneously, even when not all tasks have complete training data. It takes in partially labeled image datasets for tasks like semantic segmentation and depth estimation, and outputs more robust multi-task learning models. This is ideal for researchers working on advanced computer vision systems.
No commits in the last 6 months.
Use this if you are a computer vision researcher developing multi-task learning models and need to improve performance with incomplete or partially labeled datasets.
Not ideal if you are looking for a plug-and-play solution for a business problem, as this is a research tool for model development and not a finished application.
Stars
24
Forks
1
Language
Python
License
MIT
Category
Last pushed
May 31, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/KentoNishi/JTR-CVPR-2024"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AdaptiveMotorControlLab/CEBRA
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
theolepage/sslsv
Toolkit for training and evaluating Self-Supervised Learning (SSL) frameworks for Speaker...
PaddlePaddle/PASSL
PASSL包含 SimCLR，MoCo v1/v2，BYOL，CLIP，PixPro，simsiam, SwAV, BEiT，MAE 等图像自监督算法以及 Vision...
YGZWQZD/LAMDA-SSL
30 Semi-Supervised Learning Algorithms
ModSSC/ModSSC
ModSSC: A Modular Framework for Semi Supervised Classification