Independently optimized decoy patches redirect ViT attention-based defenses away from true adversarial regions while largely preserving attack success.
End-to- end object detection with transformers
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2roles
background 1polarities
background 1representative citing papers
DetRefiner fuses global and local features with a Transformer to refine OVOD confidence scores, delivering up to +10.1 AP gains on novel categories across multiple datasets.
citing papers explorer
-
Adversarial Decoys: Misdirecting Attention-Based Defenses in ViT
Independently optimized decoy patches redirect ViT attention-based defenses away from true adversarial regions while largely preserving attack success.
-
DetRefiner: Model-Agnostic Detection Refinement with Feature Fusion Transformer
DetRefiner fuses global and local features with a Transformer to refine OVOD confidence scores, delivering up to +10.1 AP gains on novel categories across multiple datasets.