SMSD75/Timetuning
Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations ICCV23
This project helps computer vision researchers and practitioners enhance how their AI models understand objects within images. By training a Vision Transformer on short video clips showing objects in motion, it improves the model's ability to identify and segment those objects in new images and videos. The input is a pre-trained Vision Transformer and videos of target objects, and the output is a more robust Vision Transformer capable of creating semantically rich image patch embeddings for better object segmentation.
No commits in the last 6 months.
Use this if you need to improve the spatial understanding and segmentation capabilities of your Vision Transformer models by leveraging temporal information from videos.
Not ideal if your primary task is not image or video object segmentation, or if you do not have video data readily available for training.
Stars
30
Forks
2
Language
Python
License
—
Category
Last pushed
Dec 30, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/SMSD75/Timetuning"
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