Skip to content

[AAAI-2024] Official implementation of "eTag: Class-Incremental Learning via Embedding Distillation and Task-Oriented Generation"

License

Notifications You must be signed in to change notification settings

libo-huang/eTag

Repository files navigation

eTag: Class-Incremental Learning via Hierarchical Embedding Distillation and Task-Oriented Generation

Introduction

This repository contains the key training and evaluation codes for the AAAI-2024 paper titled "eTag: Class-Incremental Learning via Hierarchical Embedding Distillation and Task-Oriented Generation".

Requirements

To run the code, ensure the following dependencies are installed:

  • Python 3.8.5
  • PyTorch 1.7.1
  • torchvision 0.8.2

How to Run

Dataset Preparation

Before running the code, ensure the dataset is properly downloaded or softly linked in the ./dataset directory.

Execution

You can test our method by executing the provided scripts or running the following commands in the ./scripts directory:

CIFAR-100 Dataset

# 5 tasks
bash -i run.sh cifar 0 5
# 10 tasks
bash -i run.sh cifar 0 10
# 25 tasks
bash -i run.sh cifar 0 25

ImageNet Subset Dataset

# 5 tasks
bash -i run.sh imagenet 0 5
# 10 tasks
bash -i run.sh imagenet 0 10
# 25 tasks
bash -i run.sh imagenet 0 25

Arguments

  • -data: Dataset name. Choose from cifar100 or imagenet_sub.
  • -log_dir: Directory to save models, logs, and events.
  • -num_task: Number of tasks after the initial task.
  • -nb_cl_fg: Number of classes in the first task.

For additional tunable arguments, refer to the opts_eTag.py file.

License

This project is licensed under the Apache License 2.0.
A permissive license that requires preservation of copyright and license notices. Contributors provide an express grant of patent rights. Licensed works, modifications, and larger works may be distributed under different terms and without source code.

Permissions Conditions Limitations
✅ Commercial use ⓘ License and copyright notice ❌ Trademark use
✅ Modification ⓘ State changes ❌ Liability
✅ Distribution ❌ Warranty
✅ Patent use
✅ Private use

About

[AAAI-2024] Official implementation of "eTag: Class-Incremental Learning via Embedding Distillation and Task-Oriented Generation"

Topics

Resources

License

Stars

Watchers

Forks