Band
Joo Seong Jeong, Jingyu Lee, Donghyun Kim, Changmin Jeon, Changjin Jeong, Youngki Lee, Byung-Gon Chun
Abstract
The rapid development of deep learning algorithms, as well as innovative hardware advancements, encourages multi-DNN workloads such as augmented reality applications. However, existing mobile inference frameworks like TensorFlow Lite and MNN fail to efficiently utilize heterogeneous processors available on mobile platforms, because they focus on running a single DNN on a specific processor. As mobile processors are too resource-limited to deliver reasonable performance for such workloads by their own, it is challenging to serve multi-DNN workloads with existing frameworks.
Topics & Concepts
Computer scienceInferenceDeep learningFocus (optics)Computer architectureMobile deviceMobile computingArtificial intelligenceResource (disambiguation)Distributed computingComputer networkOperating systemPhysicsOpticsAdvanced Neural Network ApplicationsContext-Aware Activity Recognition SystemsIoT and Edge/Fog Computing