【文件属性】:
文件名称:1506.02025_Spatial Transformer Networks
文件大小:7.89MB
文件格式:PDF
更新时间:2021-09-03 10:46:26
论文
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.