FCA/README.md

## FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attack

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

![image](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.
Update README.md 2021-09-12 16:33:38 +08:00			`## FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attack`

			`Case study of the FCA. The code can be find in [FCA]([http://]).`

			`### Cases of digital attack`

Update README.md 2021-09-12 16:34:04 +08:00			`![image](https://github.com/winterwindwang/Full-coverage-camouflage-adversarial-attack/blob/gh-pages/assets/distance_10_elevation_30_adv_pred.gif)`
Update README.md 2021-09-12 16:33:38 +08:00
			`### Cases of multi-view robust`



			`### Ablation study`

			`#### Different combination of loss terms`

Update README.md 2021-09-12 11:07:10 +08:00			`![image](https://github.com/winterwindwang/Full-coverage-camouflage-adversarial-attack/blob/gh-pages/assets/abaltion_study_loss.png)`
Update README.md 2021-09-12 16:33:38 +08:00
			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.