DART: Input-Difficulty-AwaRe Adaptive Threshold for Early-Exit DNNs

Computer Science > Hardware Architecture [Submitted on 17 Feb 2026] DART: Input-Difficulty-AwaRe Adaptive Threshold for Early-Exit DNNs Parth Patne, Mahdi Taheri, Christian Herglotz, Maksim Jenihhin, Milos Krstic, Michael Hübner 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 introduces DART (Input-Difficulty-Aware Adaptive Threshold), a framework that overcomes these limitations. DART introduces three key innovations: (1) a lightweight difficulty estimation module that quantifies input complexity with minimal computational overhead, (2) a joint exit policy optimization algorithm based on dynamic programming, and (3) an adaptive coefficient management system. Experiments on diverse DNN benchmarks (AlexNet, ResNet-18, VGG-16) demonstrate that DART achieves up to \textbf{3.3\times} speedup, \textbf{5.1\times} lower energy, and up to \textbf{42\%} lower average power compared to static networks, while preserving competitive accuracy. Extending DART to Vision Transformers (LeViT) yields power (5.0\times) and execution-time (3.6\times) gains but also accuracy loss (up to 17 percent), underscoring the need for transformer-specific early-exit mechanisms. We further introduce the Difficulty-Aware Efficiency Score (DAES), a novel multi-objective metric, under which DART achieves up to a 14.8 improvement over baselines, highlighting superior accuracy, efficiency, and robustness trade-offs. Subjects: Hardware Architecture (cs.AR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2603.12269 [cs.AR]   (or arXiv:2603.12269v1 [cs.AR] for this version)   https://doi.org/10.48550/arXiv.2603.12269 Focus to learn more Submission history From: Mahdi Taheri [view email] [v1] Tue, 17 Feb 2026 10:39:05 UTC (4,360 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AR < prev   |   next > new | recent | 2026-03 Change to browse by: cs cs.AI cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)