MrChenFeng/MaskCon_CVPR2023
MaskCon: Masked Contrastive Learning for Coarse-Labeled Dataset (CVPR2023)
This project helps machine learning practitioners improve image classification and retrieval models when precise image labels are difficult or expensive to obtain. It takes a dataset where images are grouped into broad categories and outputs a model that can distinguish between more specific sub-categories. This is ideal for data scientists and ML engineers working with large image datasets where fine-grained labeling is a bottleneck.
No commits in the last 6 months.
Use this if you have an image dataset with general categories, but you need your model to learn to recognize more detailed types of objects or attributes within those categories.
Not ideal if your dataset already has accurate, detailed labels for all images, or if your problem doesn't involve image classification or retrieval.
Stars
35
Forks
6
Language
Python
License
MIT
Category
Last pushed
Mar 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MrChenFeng/MaskCon_CVPR2023"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Westlake-AI/openmixup
CAIRI Supervised, Semi- and Self-Supervised Visual Representation Learning Toolbox and Benchmark
YU1ut/MixMatch-pytorch
Code for "MixMatch - A Holistic Approach to Semi-Supervised Learning"
kamata1729/QATM_pytorch
Pytorch Implementation of QATM:Quality-Aware Template Matching For Deep Learning
nttcslab/msm-mae
Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representations
rgeirhos/generalisation-humans-DNNs
Data, code & materials from the paper "Generalisation in humans and deep neural networks" (NeurIPS 2018)