论文标题
分辨率可切换网络用于运行时有效的图像识别
Resolution Switchable Networks for Runtime Efficient Image Recognition
论文作者
论文摘要
我们提出了一种训练单个卷积神经网络的通用方法，该神经网络能够在推理时切换图像分辨率。因此，可以选择运行速度以满足各种计算资源限制。用建议方法训练的网络被命名为“分辨率可切换网络”（RS-NETS）。基本培训框架共享用于处理分辨率不同的图像的网络参数，但可以保持单独的批准层。尽管它的设计效率很高，但它导致不同分辨率的准确性变化不一致，为此，我们从火车测试识别差异方面提供了详细的分析。进一步设计了多分辨率的合奏蒸馏，随着分辨率的加权合奏即时学习教师。多亏了合奏和知识蒸馏，与单独训练的型号相比，RS-NET在各种分辨率方面都可以进行准确的改进。提供了ImageNet数据集的广泛实验，我们还考虑了量化问题。代码和型号可在https://github.com/yikaiw/rs-nets上找到。
We propose a general method to train a single convolutional neural network which is capable of switching image resolutions at inference. Thus the running speed can be selected to meet various computational resource limits. Networks trained with the proposed method are named Resolution Switchable Networks (RS-Nets). The basic training framework shares network parameters for handling images which differ in resolution, yet keeps separate batch normalization layers. Though it is parameter-efficient in design, it leads to inconsistent accuracy variations at different resolutions, for which we provide a detailed analysis from the aspect of the train-test recognition discrepancy. A multi-resolution ensemble distillation is further designed, where a teacher is learnt on the fly as a weighted ensemble over resolutions. Thanks to the ensemble and knowledge distillation, RS-Nets enjoy accuracy improvements at a wide range of resolutions compared with individually trained models. Extensive experiments on the ImageNet dataset are provided, and we additionally consider quantization problems. Code and models are available at https://github.com/yikaiw/RS-Nets.
