tsingqguo/irad tsingqguo/irad

  • Stars
    star
    5
  • Rank 2,861,937 (Top 57 %)
  • Language
    Python
  • License
    MIT License
  • Created 9 months ago
  • Updated 7 months ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
tsingqguo/irad
github

tsingqguo

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

We introduce a novel approach to counter adversarial attacks, namely, image resampling. The underlying rationale behind our idea is that image resampling can alleviate the influence of adversarial perturbations while preserving essential semantic information, thereby conferring an inherent advantage in defending against adversarial attacks.

More Repositories

1

exposure-fusion-shadow-removal

We propose a new method for effective shadow removal by regarding it as an exposure fusion problem.
Jupyter Notebook
184
star
2

efficientderain

we propose EfficientDerain for high-efficiency single-image deraining
Python
164
star
3

misf

Python
91
star
4

DSiam

Learning Dynamic Siamese Network for Visual Object Tracking
MATLAB
38
star
5

ABBA

Python
29
star
6

inpaint4shadow

We propose the shadow-guided inpainting task to take advantage of the shadow removal and image inpainting.
Python
22
star
7

bgmix

We propose a novel data augmentation by enriching the backgrounds for change detection in a weakly-superivsed way.
Python
20
star
8

AttackTracker

Python
18
star
9

jpgnet

We proposed a novel framework for image inpainting. https://arxiv.org/abs/2107.04281
Python
17
star
10

jadena

Official implementation of "Can You Spot the Chameleon? Adversarially Camouflaging Images from Co-Salient Object Detection" in CVPR 2022.
Python
17
star
11

ABA

We propose the adversarial blur attack (ABA) against visual object tracking.
Python
12
star
12

robustOT

We build a benchmark to involve existing adversairal tracking attacks and defense methods and evaluates their performance, which could trick a series of novel works and push the progress to build a robust tracking system.
Python
7
star
13

deeprhythm

Python
6
star
14

sharel

We propose a shadow-removal benchmark dataset (i.e., SHAREL) to explore the mutual influence of shadow removal and facial landmark detection tasks.
4
star
15

tsingqguo.github.io

Homepage of Qing Guo
HTML
2
star
16

efficientderainplus

We further extend the efficientderain in https://github.com/tsingqguo/efficientderain via a novel predictive filtering framework.
Python
2
star
17

ccotssr

abc
MATLAB
1
star
18

MSiam

Try to build a new tracking framework with Siamese network
MATLAB
1
star
19

frequency-tuned-ACM

This repository contains the demos of frequency-tuned ACM.
MATLAB
1
star
20

evadingfakedetector

We propose a statistical consistency attack (StatAttack) against diverse DeepFake detectors.
1
star
21

resample4defense

We have identified a novel adversarial defense solution, i.e., image resampling, which can break the adversarial textures while maintaining the main semantic information in the input image. This work has been accepted to ICLR 2024.
1
star