Hybrid Composition with IdleBlock: More Efficient Networks for Image Recognition
This work addresses the need for simpler and more efficient network design in image recognition, offering a new direction that could impact both human-designed and neural architecture search-based networks.
The paper tackles the problem of designing efficient image recognition networks by proposing a hybrid composition with IdleBlock, which prunes connections and breaks monotonic design traditions, resulting in deeper MobileNet v3 surpassing state-of-the-art networks and hybridized EfficientNet-B0 being more efficient with similar computation budgets.
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.