p61049258
/
FCA
forked from idrl/FCA
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Update README.md

This commit is contained in:
freeneuro 2021-09-12 16:39:39 +08:00 committed by GitHub
parent 8c522e2d82
commit d53a52f359
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -4,8 +4,7 @@ Case study of the FCA. The code can be find in [FCA]([http://]).
### Cases of digital attack ### Cases of digital attack
![image](https://github.com/winterwindwang/Full-coverage-camouflage-adversarial-attack/blob/gh-pages/assets/distance_10_elevation_30_adv_pred.gif) <img src = 'https://github.com/winterwindwang/Full-coverage-camouflage-adversarial-attack/blob/gh-pages/assets/distance_10_elevation_30_adv_pred.gif?raw=true'/>
### Cases of multi-view robust ### Cases of multi-view robust
@ -14,6 +13,5 @@ Case study of the FCA. The code can be find in [FCA]([http://]).
#### Different combination of loss terms #### Different combination of loss terms
![image](https://github.com/winterwindwang/Full-coverage-camouflage-adversarial-attack/blob/gh-pages/assets/abaltion_study_loss.png) <img src = 'https://github.com/winterwindwang/Full-coverage-camouflage-adversarial-attack/blob/gh-pages/assets/abaltion_study_loss.png?raw=true'/>
As we can see from the Figure, different loss term plays different role in attacking. For example, the camouflaged car generated by `obj+smooth (we omit the smooth loss, and denotes as obj)` hardly hidden from the detector, while the camouflaged car generated by `iou` successfully suppress the detecting bounding box of the car region, and finally the camouflaged car generated by `cls` successfully make the detector to misclassify the car to anther category. As we can see from the Figure, different loss term plays different role in attacking. For example, the camouflaged car generated by `obj+smooth (we omit the smooth loss, and denotes as obj)` hardly hidden from the detector, while the camouflaged car generated by `iou` successfully suppress the detecting bounding box of the car region, and finally the camouflaged car generated by `cls` successfully make the detector to misclassify the car to anther category.