DETOUR enables practical backdoor attacks on object detectors by training with rescaled semantic triggers from real-world objects placed at multiple locations to exploit the trigger radiating effect for reliable activation under varying fields of view and spatial configurations.
In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DETOUR: A Practical Backdoor Attack against Object Detection
DETOUR enables practical backdoor attacks on object detectors by training with rescaled semantic triggers from real-world objects placed at multiple locations to exploit the trigger radiating effect for reliable activation under varying fields of view and spatial configurations.