Strategies at a glance: A comparative analysis of training techniques for optimizing early-exit deep neural networks

Early-exit deep neural networks (DNNs) enable adaptive inference by allowing predictions at intermediate layers, thereby reducing computational cost. However, their performance is highly sensitive to the chosen training strategy-a factor that remains underexplored. This study presents the first systematic comparison of six prominent strategies-Joint, Separate, Branch-wise, Two-stage, Distillation-based, and Hybrid-across three architectures (MobileNet, ResNet, VGG) using core benchmarks (CIFAR-10 and CIFAR-100). To evaluate scalability and domain generalization, we extended experiments on ImageNet-100 and ChestX-ray14. For each setup, we assess convergence behavior, accuracy, overfitting, and training efficiency, supported by statistical validation via ANOVA and Tukey's HSD tests. Results reveal key trade-offs: Joint and Distillation-based strategies offer strong generalization but incur higher computational cost; Two-stage and Branch-wise are prone to overfitting at deeper exits; Separate training underperforms at early exits. In contrast, Hybrid strategies achieve the best balance of accuracy and efficiency. These insights offer practical guidance for optimizing early-exit DNNs under resource constraints and lay a principled foundation for future research on efficient training paradigms.