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)
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.
Stars
49
Forks
7
Language
Python
License
—
Category
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.
Higher-rated alternatives
oscarknagg/few-shot
Repository for few-shot learning machine learning projects
jakesnell/prototypical-networks
Code for the NeurIPS 2017 Paper "Prototypical Networks for Few-shot Learning"
harveyslash/Facial-Similarity-with-Siamese-Networks-in-Pytorch
Implementing Siamese networks with a contrastive loss for similarity learning
google-research/meta-dataset
A dataset of datasets for learning to learn from few examples
akshaysharma096/Siamese-Networks
Few Shot Learning by Siamese Networks, using Keras.