srvCodes/continual_learning_with_vit
Code for our CVPR 2022 workshop paper "Towards Exemplar-Free Continual Learning in Vision Transformers"
This project helps machine learning researchers improve how Vision Transformers (ViTs) learn new image classification tasks over time without forgetting previously learned information. It provides code implementing new methods for 'exemplar-free continual learning', meaning it doesn't need to store old training examples. Researchers can input a sequence of image classification tasks and output a ViT model that efficiently learns each new task while retaining knowledge from previous ones.
No commits in the last 6 months.
Use this if you are a machine learning researcher or practitioner working with Vision Transformers and need to implement or evaluate advanced continual learning strategies for image classification.
Not ideal if you are looking for an out-of-the-box solution for deploying a continually learning system without deep expertise in machine learning research.
Stars
24
Forks
4
Language
Python
License
MIT
Category
Last pushed
Jul 10, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/srvCodes/continual_learning_with_vit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
galilai-group/stable-pretraining
Reliable, minimal and scalable library for pretraining foundation and world models
CognitiveAISystems/MAPF-GPT
[AAAI-2025] This repository contains MAPF-GPT, a deep learning-based model for solving MAPF...
UKPLab/gpl
Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled...
larslorch/avici
Amortized Inference for Causal Structure Learning, NeurIPS 2022
svdrecbd/mhc-mlx
MLX + Metal implementation of mHC: Manifold-Constrained Hyper-Connections by DeepSeek-AI.