I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors(CVPR 2021)

A Pytorch Implementation of "I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors".

Introduction

Please follow ssd.pytorch respository to setup the environment. In this project, we use Pytorch 1.0.1 and CUDA version is 10.0.130.

Datasets

PASCAL_VOC 07+12: Please follow the instruction to prepare VOC dataset.
Clipart/WaterColor/Comic: Please follow the instruction to prepare dataset.

Pre-trained Models

First download the fc-reduced VGG-16 PyTorch base network weights at: https://s3.amazonaws.com/amdegroot-models/vgg16_reducedfc.pth
By default, we assume you have downloaded the file in the ssd.pytorch/weights dir:

mkdir weights
cd weights
wget https://s3.amazonaws.com/amdegroot-models/vgg16_reducedfc.pth

Train

CUDA_VISIBLE_DEVICES=$GPU_ID \
       python train_I3N.py \
       --name file_name\
       --dataset source_dataset --dataset_target target_dataset \
       --basenet path_to_model

Test

CUDA_VISIBLE_DEVICES=$GPU_ID \
       python eval_I3N.py \
       --dataset target_dataset\
       --trained_model_path path_to_model

Citation

If you find this repository useful, please cite our paper:

@inproceedings{CHEN_2021_I3NET,
  title={I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors},
  author={Chen, Chaoqi and Zheng, Zebiao and Huang, Yue and Ding, Xinghao and Yu, Yizhou},
  booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2021}
}