Early-exit networks reduce inference cost by allowing ``easy'' inputs to stop early, but practical deployment hinges on knowing \emph{when} early exit is safe. We introduce SAFE-KD, a universal multi-exit wrapper for modern vision backbones that couples hierarchical distillation with \emph{conformal risk control}. SAFE-KD attaches lightweight exit heads at intermediate depths, distills a strong teacher into all exits via Decoupled Knowledge Distillation (DKD), and enforces deep-to-shallow consistency between exits. At inference, we calibrate per-exit stopping thresholds on a held-out set using conformal risk control (CRC) to guarantee a user-specified \emph{selective} misclassification risk (among the samples that exit early) under exchangeability. Across multiple datasets and architectures, SAFE-KD yields improved accuracy compute trade-offs, stronger calibration, and robust performance under corruption while providing finite-sample risk guarantees.
Bridging Efficiency and Safety: Formal Verification of Neural Networks with Early Exits
The Hebrew University of Jerusalem, Israel（特拉维夫大学）；Bar Ilan University, Israel（巴伊兰大学）；Ben-Gurion University of the Negev, Israel（贝纳亚克大学）；University of California, Riverside, USA（加州大学河滨分校）
Balancing Stability and Plasticity in Sequentially Trained Early-Exiting Neural Networks
TICLab, International University of Rabat, Morocco（拉巴特国际大学TIC实验室，摩洛哥）；College of Computing, University Mohammed VI Polytechnic, Morocco（摩洛哥穆莱·伊斯梅尔Polytechnic大学计算机学院）；School of Electronic and Electrical Engineering, University of Leeds, UK（利兹大学电子与电气工程学院）
How to Train Your Multi-Exit Model? Analyzing the Impact of Training Strategies
Jagiellonian University（雅盖隆大学）；University of Warsaw（华沙大学）；Warsaw University of Technology（华沙技术大学）；IDEAS Research Institute（IDEAS研究所）；Department of Information Engineering, Electronics, and Telecommunications (DIET) at Sapienza, University of Rome, Italy（罗马大学萨皮恩扎信息工程、电子与电信系）；Wroclaw University of Science and Technology（波兹南科学与技术大学）
Unsupervised Domain Adaptation (UDA) aims to leverage a label-rich source domain to solve tasks on a related unlabeled target domain. It is a challenging problem especially when a large domain gap lies between the source and target domains. In this paper we propose a novel solution named SSRT (Safe Self-Refinement for Transformer-based domain adaptation), which brings improvement from two aspects. First, encouraged by the success of vision transformers in various vision tasks, we arm SSRT with a transformer backbone. We find that the combination of vision transformer with simple adversarial ad…
Deep Neural Networks (DNNs) are generally designed as sequentially cascaded differentiable blocks/layers with a prediction module connected only to its last layer. DNNs can be attached with prediction modules at multiple points along the backbone where inference can stop at an intermediary stage without passing through all the modules. The last exit point may offer a better prediction error but also involves more computational resources and latency. An exit point that is `optimal' in terms of both prediction error and cost is desirable. The optimal exit point may depend on the latent distribut…
Department of Computer Science, Control and Management Engineering, Sapienza University of Rome, Rome, Italy（计算机科学与控制管理工程系，罗马萨皮恩扎大学，意大利罗马）；Institute of Information Science and Technologies "Alessandro Faedo" - ISTI-CNR, Pisa, Italy（信息科学与技术研究所 "Alessandro Faedo" - ISTI-CNR，意大利比萨）；Information Engineering Department, University of Pisa, Pisa, Italy（信息工程系，比萨大学，意大利比萨）；CNRS, i3S, Inria（国家科学研究中心 CNRS、i3S、Inria）
