ADCT / README.md
Continual-Mega's picture
Update README.md
cba7a73 verified
---
license: cc-by-nc-4.0
datasets:
- Continual-Mega/Continual-MEGA-Benchmark
---
# 🧠 Continual-MEGA: A Large-scale Benchmark for Generalizable Continual Anomaly Detection
This repository contains the evaluation code for the **Continual-Mega** benchmark.
We provide the checkpoint files of the proposed model along with the evaluation code for the Continual-Mega benchmark.
The training code will be made publicly available at a later date.
πŸ”— **Codebase**: [Continual-Mega/Continual-Mega](https://github.com/Continual-Mega/Continual-Mega)
---
## πŸš€ Overview
Continual-MEGA introduces a realistic and large-scale benchmark for **continual anomaly detection** that emphasizes generalizability across domains and tasks.
The benchmark features:
- βœ… Diverse anomaly types across domains
- πŸ” Class-incremental continual learning setup
- πŸ“ˆ A large-scale evaluation protocol surpassing previous benchmarks
This repository hosts pretrained **model checkpoints** used in various scenarios defined in the benchmark.
---
## πŸ“¦ Available Checkpoints
| Model Name | Scenario | Task | Description |
|---------------------------------------|------------|-------------------------|----------------------------------------------------------|
| `scenario2/prompt_maker` | Scenario 2 | Base | Prompt maker trained on Scenario 2 base classes |
| `scenario2/adapters_base` | Scenario 2 | Base | Adapter trained on Scenario 2 base classes |
| `scenario2/30classes/adapters_task1` | Scenario 2 | Task 1 (30 classes) | Adapter trained on Task 1 (30 classes) in Scenario 2 |
| `scenario2/30classes/adapters_task2` | Scenario 2 | Task 2 (30 classes) | Adapter trained on Task 2 (30 classes) in Scenario 2 |
| *(More to come)* | – | – | – |
---
## πŸ›  Usage Example
### Continual Setting Evaluation
```
sh eval_continual.sh
```
### Zero-Shot Evaluation
```
sh eval_zero.s