MINA: Multi-Input Network Augmentation for Enhancing Tiny Deep Learning

Network Augmentation (NetAug) is a recent method used to improve the performance of tiny neural networks on large-scale datasets. This provides additional supervision models from larger augmented models, mitigating issue underfitting. However, capacity not fully utilized, resulting in underutilization resources. In order utilize model without exacerbating underfitting model, we propose new called Multi-Input (MINA). MINA converts into multi-input configuration, allowing only receive more diverse inputs during training. Additionally, network can be converted back their original single-input configuration after Our extensive experiments datasets demonstrate that effective improving networks. We also consistently downstream tasks, such as fine-grained image classification tasks and object detection tasks.