Efficient Adaptive Inference leveraging Bag-of-Features-based Early Exits

Early exits provide an effective way of implementing adaptive computational graphs over deep learning models. In this way it is possible to adapt them on-the-fly to the available computational resources or even to the difficulty of each input sample, reducing the energy and computational power requirements in many embedded and mobile applications. However, performing this kind of adaptive inference also comes with several challenges, since the difficulty of each sample must be estimated and the most appropriate early exit must be selected. It is worth noting that existing approaches often lead to highly unbalanced distributions over the selected early exits, reducing the efficiency of the adaptive inference process. At the same time, only a few resources can be devoted to the aforementioned process, in order to ensure that an adequate speedup will be obtained. The main contribution of this work is to provide an easy to use and tune adaptive inference approach for early exits that can overcome some of these limitations. In this way, the proposed method allows for a) obtaining a more balanced inference distribution among the early exits, b) relying on a single and interpretable hyper-parameter for tuning its behavior (ranging from faster inference to higher accuracy), and c) improving the performance of the networks (increasing the accuracy and reducing the time needed for inference). Indeed, the effectiveness of the proposed method over existing approaches is demonstrated using four different image datasets.