keyu-tian/SparK

[ICLR'23 SpotlightšŸ”„] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"

42
/ 100
Emerging

SparK is a deep learning technique that significantly improves the performance of convolutional neural networks (CNNs) for image analysis tasks. It takes standard image datasets and a CNN architecture as input, then applies a self-supervised pretraining method to produce a more powerful, "pretrained" CNN. This pretrained model can then be used to achieve higher accuracy on various image classification benchmarks. It is designed for machine learning researchers and practitioners who work with computer vision models.

1,368 stars. No commits in the last 6 months.

Use this if you want to improve the performance of your existing convolutional neural network models for image-related tasks without needing a large amount of labeled data for initial training.

Not ideal if you are working with non-image data or if your project does not involve deep learning for computer vision.

computer-vision image-classification deep-learning model-pretraining self-supervised-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

1,368

Forks

84

Language

Python

License

MIT

Last pushed

Jan 23, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/keyu-tian/SparK"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.