EIVE: End-to-End Instance-Specific Visual Explanations for Detection Transformers

ArXi:2606.01601v1 Announce Type: new Visual explainability for object detection remains challenging due to the multi-instance nature of detection. Existing approaches predominantly adopt post-hoc paradigms, such as gradient-based or perturbation-based explanation methods, to interpret pretrained detectors. However, these methods require additional gradient computation or repeated model inference, resulting in limited efficiency.