Revisiting Data Augmentation for Rotational Invariance in Convolutional Neural Networks

Abstract

Convolutional Neural Networks (CNN) offer state of the art performance in various computer vision tasks. Many of those tasks require different subtypes of affine invariances (scale, rotational, translational) to image transformations. Convolutional layers are translation equivariant by design, but in their basic form lack invariances. In this work we investigate how best to include rotational invariance in a CNN for image classification. Our experiments show that networks trained with data augmentation alone can classify rotated images nearly as well as in the normal unrotated case; this increase in representational power comes only at the cost of training time. We also compare data augmentation versus two modified CNN models for achieving rotational invariance or equivariance, Spatial Transformer Networks and Group Equivariant CNNs, finding no significant accuracy increase with these specialized methods. In the case of data augmented networks, we also analyze which layers help the network to encode the rotational invariance, which is important for understanding its limitations and how to best retrain a network with data augmentation to achieve invariance to rotation.

References in corpus (2)

• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Learning rotation invariant convolutional filters for texture classification

Cited by in corpus (5)

• Accelerating Material Property Prediction using Generically Complete Isometry Invariants
• Invariance Measures for Neural Networks
• Application of Computer Vision Techniques for Segregation of PlasticWaste based on Resin Identification Code
• Attribute-Based Robotic Grasping with One-Grasp Adaptation
• Efficient Rotation Invariance in Deep Neural Networks through Artificial Mental Rotation