Learning Translation Invariance in CNNs
arXiv:2011.11757
Abstract
When seeing a new object, humans can immediately recognize it across different retinal locations: we say that the internal object representation is invariant to translation. It is commonly believed that Convolutional Neural Networks (CNNs) are architecturally invariant to translation thanks to the convolution and/or pooling operations they are endowed with. In fact, several works have found that these networks systematically fail to recognise new objects on untrained locations. In this work we show how, even though CNNs are not 'architecturally invariant' to translation, they can indeed 'learn' to be invariant to translation. We verified that this can be achieved by pretraining on ImageNet, and we found that it is also possible with much simpler datasets in which the items are fully translated across the input canvas. We investigated how this pretraining affected the internal network representations, finding that the invariance was almost always acquired, even though it was some times disrupted by further training due to catastrophic forgetting/interference. These experiments show how pretraining a network on an environment with the right 'latent' characteristics (a more naturalistic environment) can result in the network learning deep perceptual rules which would dramatically improve subsequent generalization.
NeurIPS 2020 Workshop SVRHM
References in corpus (11)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- EMNIST: an extension of MNIST to handwritten letters
- Deep Learning: A Critical Appraisal
- Making Convolutional Networks Shift-Invariant Again
- Scale-Invariant Convolutional Neural Networks
- Quantifying Translation-Invariance in Convolutional Neural Networks
- Learning to Continually Learn
- A neural network walks into a lab: towards using deep nets as models for human behavior
- Minimal Images in Deep Neural Networks: Fragile Object Recognition in Natural Images
- Representation of White- and Black-Box Adversarial Examples in Deep Neural Networks and Humans: A Functional Magnetic Resonance Imaging Study