ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks

Abstract

As designing appropriate Convolutional Neural Network (CNN) architecture in the context of a given application usually involves heavy human works or numerous GPU hours, the research community is soliciting the architecture-neutral CNN structures, which can be easily plugged into multiple mature architectures to improve the performance on our real-world applications. We propose Asymmetric Convolution Block (ACB), an architecture-neutral structure as a CNN building block, which uses 1D asymmetric convolutions to strengthen the square convolution kernels. For an off-the-shelf architecture, we replace the standard square-kernel convolutional layers with ACBs to construct an Asymmetric Convolutional Network (ACNet), which can be trained to reach a higher level of accuracy. After training, we equivalently convert the ACNet into the same original architecture, thus requiring no extra computations anymore. We have observed that ACNet can improve the performance of various models on CIFAR and ImageNet by a clear margin. Through further experiments, we attribute the effectiveness of ACB to its capability of enhancing the model's robustness to rotational distortions and strengthening the central skeleton parts of square convolution kernels.

arXiv commentAccepted to ICCV 2019

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Practical Bayesian Optimization of Machine Learning Algorithms
• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
• Wide Residual Networks
• Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
• ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
• Speeding up Convolutional Neural Networks with Low Rank Expansions
• Flattened Convolutional Neural Networks for Feedforward Acceleration
• Approximated Oracle Filter Pruning for Destructive CNN Width Optimization

Cited by in corpus (3)

• NTIRE 2020 Challenge on Image Demoireing: Methods and Results
• Multi-objective Evolutionary Approach for Efficient Kernel Size and Shape for CNN
• Unsupervised Hyperspectral Mixed Noise Removal Via Spatial-Spectral Constrained Deep Image Prior