We propose a new building block, IdleBlock, which naturally prunes connections within the block. To fully utilize the IdleBlock we break the tradition of monotonic design in state-of-the-art networks, and introducing hybrid composition with IdleBlock. We study hybrid composition on MobileNet v3 and EfficientNet-B0, two of the most efficient networks. Without any neural architecture search, the deeper "MobileNet v3" with hybrid composition design surpasses possibly all state-of-the-art image recognition network designed by human experts or neural architecture search algorithms. Similarly, the hybridized EfficientNet-B0 networks are more efficient than previous state-of-the-art networks with similar computation budgets. These results suggest a new simpler and more efficient direction for network design and neural architecture search.
@article{arxiv.1911.08609,
title = {Hybrid Composition with IdleBlock: More Efficient Networks for Image Recognition},
author = {Bing Xu and Andrew Tulloch and Yunpeng Chen and Xiaomeng Yang and Lin Qiao},
journal= {arXiv preprint arXiv:1911.08609},
year = {2019}
}