PAD

Code for the paper "PAD: Patch-Agnostic Defense against Adversarial Patch Attacks" (CVPR 2024)

Generate Convert Improve

Install / Use

/learn @Lihua-Jing/PAD

About this skill

Quality Score

0/100

README

PAD

This is the code of the paper "PAD: Patch-Agnostic Defense against Adversarial Patch Attacks", without parallel acceleration.

Setup

conda create --name pad python=3.8 conda activate pad pip install -r requirements.txt

Usage

python run-PAD.py Remember to replace the file path with your own. input_path: the dir path of the attacked images save_path: the dir path where you want to save the defended images

Related Skills

node-connect

343.1k

Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps

frontend-design

90.0k

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

openai-whisper-api

343.1k

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

qqbot-media

343.1k

QQBot 富媒体收发能力。使用 <qqmedia> 标签，系统根据文件扩展名自动识别类型（图片/语音/视频/文件）。