Probabilistic Spatial Transformer Networks

Abstract

Spatial Transformer Networks (STNs) estimate image transformations that can improve downstream tasks by `zooming in' on relevant regions in an image. However, STNs are hard to train and sensitive to mis-predictions of transformations. To circumvent these limitations, we propose a probabilistic extension that estimates a stochastic transformation rather than a deterministic one. Marginalizing transformations allows us to consider each image at multiple poses, which makes the localization task easier and the training more robust. As an additional benefit, the stochastic transformations act as a localized, learned data augmentation that improves the downstream tasks. We show across standard imaging benchmarks and on a challenging real-world dataset that these two properties lead to improved classification performance, robustness and model calibration. We further demonstrate that the approach generalizes to non-visual domains by improving model performance on time-series data.

UAI 2022

References in corpus (9)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• On Calibration of Modern Neural Networks
• Weight Uncertainty in Neural Networks
• Multivariate Confidence Calibration for Object Detection
• Recurrent Spatial Transformer Networks
• Learning Invariances using the Marginal Likelihood
• Learning Invariances in Neural Networks
• Last Layer Marginal Likelihood for Invariance Learning