A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion

ArXi:2501.07451v4 Announce Type: replace Model compression is essential in the deployment of large Computer Vision models on embedded devices. However, static optimization techniques (e.g. pruning, quantization, etc.) neglect the fact that different inputs have different complexities, thus requiring different amount of computations. Dynamic Neural Networks allow to condition the number of computations to the specific input. The current literature on the topic is very extensive and fragmented.