p49187362
/
FCA
forked from idrl/FCA
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

update

This commit is contained in:
freeneuro 2021-09-11 23:03:44 +08:00
parent 3b1525cfad
commit f62e0004b0
2 changed files with 9 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
assets/abaltion_study_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 2.2 MiB

10
index.md
View File

@ -4,12 +4,20 @@ Case study of the FCA. The code can be find in [FCA]([http://]).
### 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]
### Cases of multi-view robust
### Ablation study
#### Different combination of loss terms
![](https://github.com/winterwindwang/Full-coverage-camouflage-adversarial-attack/blob/gh-pages/assets/abaltion_study_loss.png)
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.
### Markdown
Markdown is a lightweight and easy-to-use syntax for styling your writing. It includes conventions for