PRIS-CV/On-the-fly-Category-Discovery
Code release for Your “On-the-fly Category Discovery (CVPR 2023)”
This project helps computer vision researchers and AI system developers to build models that can instantly identify and categorize new types of objects or visual patterns they haven't seen before. It takes in visual data (images or video frames) and outputs a recognition model capable of categorizing both known and novel items without needing to be retrained for each new category. This is for those building systems that need to adapt quickly to evolving visual information, like in robotics or automated surveillance.
No commits in the last 6 months.
Use this if you need a computer vision model to rapidly recognize and classify previously unknown categories of visual data in real-time, without requiring a complete system overhaul or extensive re-training.
Not ideal if your system only ever needs to classify a fixed set of predefined categories, as this project focuses on the discovery of entirely new classes.
Stars
56
Forks
3
Language
Python
License
MIT
Category
Last pushed
Jul 15, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/PRIS-CV/On-the-fly-Category-Discovery"
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