Physically adversarial attacks can mislead detectors in the real world and have attracted increasing attention. However, most existing works directly manipulate the model’s final outputs as attack objects while ignoring the inherent characteristics of objects such as multi-scale features, which are easily trapped into model-specific local optimum and degrade the transferability. To address this issue, we propose the Multi-scale Feature-aware Attack (MFA) to generate adversarial camouflages with strong attacking ability and transferability by disrupting multi-scale object-aware critical features. Specifically, we adopt the location and category information of the detector outputs to assign attribution scores to different scale feature layers. Then, we weight each feature according to their attribution results and design a pixel-level loss function in the opposite optimized direction of object detection to generate adversarial camouflages. We conduct extensive experiments in both the digital and physical world on ten detection models (e.g., the up-to-date yolov7) and significantly demonstrate the superior performance of the proposed MFA. Our Code will be available at: https://github.com/ChenWen1997/MFA.
mfa's Introduction
mfa's People
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.