Joint architecture and knowledge distillation in CNN for Chinese text recognition

•We propose a guideline to distill the architecture and knowledge of pre-trained standard CNNs simultaneously for fast compression and acceleration.•The effectiveness is first verified on offline HCTR. Compared with the baseline CNN, the corresponding compact network can reduce the computational cost by >10×and model size by >8×with negligible accuracy loss.•Furthermore, the proposed method is successfully used to reduce resource consumption of the mainstream backbone networks on CTW and MNIST.