/CPR

This repository is the code of our paper "Conditional Prototype Rectification Prompt Learning".

Primary LanguagePython

CPR

This repository is the code of our paper "Conditional Prototype Rectification Prompt Learning".

1 Environment Requirements

To run our code you need to install Dassl and the basic torch environment.

2 Dataset Setup

We suggest putting all datasets under the same folder (say $DATA) to ease management and following the instructions below to organize datasets to avoid modifying the source code. The file structure looks like

$DATA/
|–– imagenet/
|–– caltech-101/
|–– oxford_pets/
|–– stanford_cars/

If you have some datasets already installed somewhere else, you can create symbolic links in $DATA/dataset_name that point to the original data to avoid duplicate download.

The instructions to prepare each dataset are detailed below. To ensure reproducibility and fair comparison for future work, we utilize CoOp-style train/val/test splits for all datasets except ImageNet where the validation set is used as test set.

ImageNet

  • Create a folder named imagenet/ under $DATA.
  • Create images/ under imagenet/.
  • Download the dataset from the official website and extract the training and validation sets to $DATA/imagenet/images. The directory structure should look like
imagenet/
|–– images/
|   |–– train/ # contains 1,000 folders like n01440764, n01443537, etc.
|   |–– val/
  • If you had downloaded the ImageNet dataset before, you can create symbolic links to map the training and validation sets to $DATA/imagenet/images.
  • Download the classnames.txt to $DATA/imagenet/ from this link. The class names are copied from CLIP.

Caltech101

The directory structure should look like

caltech-101/
|–– 101_ObjectCategories/
|–– split_zhou_Caltech101.json

OxfordPets

The directory structure should look like

oxford_pets/
|–– images/
|–– annotations/
|–– split_zhou_OxfordPets.json

StanfordCars

The directory structure should look like

stanford_cars/
|–– cars_test\
|–– cars_test_annos_withlabels.mat
|–– cars_train\
|–– devkit\
|–– split_zhou_StanfordCars.json

Flowers102

The directory structure should look like

oxford_flowers/
|–– cat_to_name.json
|–– imagelabels.mat
|–– jpg/
|–– split_zhou_OxfordFlowers.json

Food101

The directory structure should look like

food-101/
|–– images/
|–– license_agreement.txt
|–– meta/
|–– README.txt
|–– split_zhou_Food101.json

FGVCAircraft

The directory structure should look like

fgvc_aircraft/
|–– images/
|–– ... # a bunch of .txt files

SUN397

The directory structure should look like

sun397/
|–– SUN397/
|–– split_zhou_SUN397.json
|–– ... # a bunch of .txt files

DTD

The directory structure should look like

dtd/
|–– images/
|–– imdb/
|–– labels/
|–– split_zhou_DescribableTextures.json

EuroSAT

The directory structure should look like

eurosat/
|–– 2750/
|–– split_zhou_EuroSAT.json

UCF101

  • Create a folder named ucf101/ under $DATA.
  • Download the zip file UCF-101-midframes.zip from here and extract it to $DATA/ucf101/. This zip file contains the extracted middle video frames.
  • Download split_zhou_UCF101.json from this link.

The directory structure should look like

ucf101/
|–– UCF-101-midframes/
|–– split_zhou_UCF101.json

3 Training and Testing

For few-shot learning tasks, you need to set base2new to False in main.py and modify backbone to RN50 in yaml to run code in the following format:

python main.py --config ./configs/fgvc.yaml --shots 1 --model CPR --subsample all

For few-shot learning tasks, you need to set base2new to False in main.py and modify backbone to ViT in yaml to run code in the following format:

python main.py --config ./configs/fgvc.yaml --shots 16 --model CPR --subsample base