2015/06/05 by Max Jaderberg, Karen Simonyan, Jaderberg, Max +5 · 1 voice · 104 citations
Computer Science · Engineering · Mathematics · #Advanced Image and Video Retrieval Techniques #Algorithm #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Convolutional neural network #Differentiable function #Domain Adaptation and Few-Shot Learning #Engineering #FOS: Computer and information sciences #Image warping #Mathematics #Multimodal Machine Learning Applications #Pattern recognition (psychology) #Transformer #Voltage #cs.CV
paper · pdf · doi:10.48550/arxiv.1506.02025
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2015/06/05 · arxiv published 2015/06/05 · arxiv created 2016/02/04 · arxiv updated 2016/02/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Convolutional Neural Networks define an exceptionally powerful class of models, but are still limited by the lack of ability to be spatially invariant to the input data in a computationally and parameter efficient manner. In this work we introduce a new learnable module, the Spatial Transformer, which explicitly allows the spatial manipulation of data within the network. This differentiable module can be inserted into existing convolutional architectures, giving neural networks the ability to actively spatially transform feature maps, conditional on the feature map itself, without any extra training supervision or modification to the optimisation process. We show that the use of spatial transformers results in models which learn invariance to translation, scale, rotation and more generic warping, resulting in state-of-the-art performance on several benchmarks, and for a number of classes of transformations.