[CVPR 2021] Pytorch implementation of Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs

Last update: Sep 05, 2022

Overview

Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs

In this work, we propose a framework HijackGAN, which enables non-linear latent space traversal and gain high-level controls, e.g., attributes, head poses, and landmarks, over unconditional image generation GANs in a fully black-box setting. It opens up the possibility of reusing GANs while raising concerns about unintended usage.

[Paper (CVPR 2021)][Project Page]

Prerequisites

Install required packages

pip install -r requirements.txt

Download pretrained GANs

Download the CelebAHQ pretrained weights of ProgressiveGAN [paper][code] and StyleGAN [paper][code], and then put those weights in ./models/pretrain. For example,

pretrain/
├── Pretrained_Models_Should_Be_Placed_Here
├── karras2018iclr-celebahq-1024x1024.pkl
├── karras2019stylegan-celebahq-1024x1024.pkl
├── pggan_celebahq_z.pt
├── stylegan_celebahq_z.pt
├── stylegan_headpose_z_dp.pt
└── stylegan_landmark_z.pt

Quick Start

Specify number of images to edit, a model to generate images, some parameters for editting.

LATENT_CODE_NUM=1
python edit.py \
    -m pggan_celebahq \
    -b boundaries/ \
    -n "$LATENT_CODE_NUM" \
    -o results/stylegan_celebahq_eyeglasses \
    --step_size 0.2 \
    --steps 40 \
    --attr_index 0 \
    --task attribute \
    --method ours

Usage

Important: For different given images (initial points), different step size and steps may be considered. In the following examples, we provide the parameters used in our paper. One could adjust them for better performance.

Specify Number of Samples

LATENT_CODE_NUM=1

Unconditional Modification

python edit.py \
    -m pggan_celebahq \
    -b boundaries/ \
    -n "$LATENT_CODE_NUM" \
    -o results/stylegan_celebahq_smile_editing \
    --step_size 0.2 \
    --steps 40 \
    --attr_index 0\
    --task attribute

Conditional Modification

python edit.py \
    -m pggan_celebahq \
    -b boundaries/ \
    -n "$LATENT_CODE_NUM" \
    -o results/stylegan_celebahq_smile_editing \
    --step_size 0.2 \
    --steps 40 \
    --attr_index 0\
    --condition\
    -i codes/pggan_cond/age.npy
    --task attribute

Head pose

Pitch

python edit.py \
    -m stylegan_celebahq \
    -b boundaries/ \
    -n "$LATENT_CODE_NUM" \
    -o results/ \
    --task head_pose \
    --method ours \
    --step_size 0.01 \
    --steps 2000 \
    --attr_index 1\
    --condition\
    --direction -1 \
    --demo

Yaw

python edit.py \
    -m stylegan_celebahq \
    -b boundaries/ \
    -n "$LATENT_CODE_NUM" \
    -o results/ \
    --task head_pose \
    --method ours \
    --step_size 0.1 \
    --steps 200 \
    --attr_index 0\
    --condition\
    --direction 1\
    --demo

Landmarks

Parameters for reference: (attr_index, step_size, steps) (4: 0.005 400) (5: 0.01 100), (6: 0.1 200), (8 0.1 200)

CUDA_VISIBLE_DEVICES=0 python edit.py \
    -m stylegan_celebahq \
    -b boundaries/ \
    -n "$LATENT_CODE_NUM" \
    -o results/ \
    --task landmark \
    --method ours \
    --step_size 0.1 \
    --steps 200 \
    --attr_index 6\
    --condition\
    --direction 1 \
    --demo

Generate Balanced Data

This a templeate showing how we generated balanced data for attribute manipulation (16 attributes in our internal experiments). You can modify it to fit your task better. Please first refer to here and replace YOUR_TASK_MODEL with your own classification model, and then run:

NUM=500000
CUDA_VISIBLE_DEVICES=0 python generate_balanced_data.py -m stylegan_celebahq \
    -o ./generated_data -K ./generated_data/indices.pkl -n "$NUM" -SI 0 --no_generated_imgs

[CVPR 2021] Pytorch implementation of Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs

Related tags

Overview

Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs

Prerequisites

Install required packages

Download pretrained GANs

Quick Start

Usage

Specify Number of Samples

Unconditional Modification

Conditional Modification

Head pose

Pitch

Yaw

Landmarks

Generate Balanced Data

Evaluations

TO-DO

Acknowledgment

Owner

Hui-Po Wang

Using Random Effects to Account for High-Cardinality Categorical Features and Repeated Measures in Deep Neural Networks

CarND-LaneLines-P1 - Lane Finding Project for Self-Driving Car ND

Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting

Optimizing Value-at-Risk and Conditional Value-at-Risk of Black Box Functions with Lacing Values (LV)

A collection of papers about Transformer in the field of medical image analysis.

Computational Methods Course at UdeA. Forked and size reduced from:

Checkout some cool self-projects you can try your hands on to curb your boredom this December!

A python package to perform same transformation to coco-annotation as performed on the image.

Transfer-Learn is an open-source and well-documented library for Transfer Learning.

This is the official code for the paper "Ad2Attack: Adaptive Adversarial Attack for Real-Time UAV Tracking".

Rank 3 : Source code for OPPO 6G Data Generation Challenge

RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth, in ICCV 2021 (oral)

ICCV2021 - Mining Contextual Information Beyond Image for Semantic Segmentation

Predicting Student Attentiveness using OpenCV

A graphical Semi-automatic annotation tool based on labelImg and Yolov5

[Pedestron] Generalizable Pedestrian Detection: The Elephant In The Room. @ CVPR2021

Explore extreme compression for pre-trained language models

A curated list and survey of awesome Vision Transformers.

Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation

Array Camera Ptychography