AI RESEARCH
DART: Input-Difficulty-AwaRe Adaptive Threshold for Early-Exit DNNs
arXiv CS.AI
•
ArXi:2603.12269v1 Announce Type: cross Early-exit deep neural networks enable adaptive inference by terminating computation when sufficient confidence is achieved, reducing cost for edge AI accelerators in resource-constrained settings. Existing methods, however, rely on suboptimal exit policies, ignore input difficulty, and optimize thresholds independently. This paper