leesb7426/CVPR2022-Task-Discrepancy-Maximization-for-Fine-grained-Few-Shot-Classification

Official PyTorch Repository of "Task Discrepancy Maximization for Fine-grained Few-Shot Classification" (TDM, CVPR 2022 Oral Paper)

29
/ 100
Experimental

This project helps researchers and machine learning practitioners quickly and accurately identify very specific categories within images, even when they have very few examples for each category. You input image datasets with many fine-grained classes (like different bird species or car models) and it provides a trained model capable of classifying new, similar images with high precision. This is ideal for those working in fields like ecological surveys, industrial quality control, or medical imaging.

No commits in the last 6 months.

Use this if you need to classify images into highly specific categories with limited training data per category, such as distinguishing between subtle differences in animal breeds or machinery parts.

Not ideal if you have abundant labeled data for all your image categories or if you are working with broad, rather than fine-grained, classification tasks.

image-classification fine-grained-categorization low-data-learning computer-vision-research pattern-recognition
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

49

Forks

7

Language

Python

License

Last pushed

Nov 21, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/leesb7426/CVPR2022-Task-Discrepancy-Maximization-for-Fine-grained-Few-Shot-Classification"

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