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 2021-09-13 09:35:21 +08:00 committed by GitHub
parent 0642027431
commit 4e6f676b6a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -2,7 +2,7 @@
Case study of the FCA. The code can be find in [FCA](https://github.com/winterwindwang/Full-coverage-camouflage-adversarial-attack/tree/gh-pages/src). Case study of the FCA. The code can be find in [FCA](https://github.com/winterwindwang/Full-coverage-camouflage-adversarial-attack/tree/gh-pages/src).
### Cases of digital attack ### Cases of Digital Attack
#### Carmear distance is 3 #### Carmear distance is 3
@ -51,7 +51,7 @@ Case study of the FCA. The code can be find in [FCA](https://github.com/winterwi
</tr> </tr>
</table> </table>
### Cases of multi-view robust ### Cases of Multi-view Attack
@ -107,7 +107,7 @@ The first row is the original detection result. The second row is the camouflage
<img src = 'https://github.com/winterwindwang/Full-coverage-camouflage-adversarial-attack/blob/gh-pages/assets/abaltion_study_loss.png?raw=true'/> <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 terms plays different roles in attacking. For example, the camouflaged car generated by `obj+smooth (we omit the smooth loss, and denotes as obj)` can hidden the vehicle successfully, while the camouflaged car generated by `iou` can 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.
#### Different initialization ways #### Different initialization ways