PLZSL

This repository contains the reference code for the paper "Partial Label Zero Shot Learning with Semantic Mining and Instance-Label Alignment".

🌈 Model Architecture

📚 Dependencies

• Python 3.11
• PyTorch = 2.0.0
• All experiments are performed on a single RTX 4090 GPU.

⚡ Dataset

• Please download datasets and place them on your local machine, then update the dataset root paths in the code accordingly.
• CUB, AWA2 can be downloaded here.
• CIFAR-10 / CIFAR-100: automatically downloadable via torchvision.
• Food-101 / Flowers-102: please contact us for access/instructions (or update this section if you later provide public download scripts).

🚀 Train & Eval

Before running, please set the correct dataset paths in

./lib/dataset/...

Then modify the relevant hyperparameters if needed, and run

python main.py