Link to paper: [1506.02025] Spatial Transformer Networks
This paper introduces a neural networks module that can learn input-dependent spatial transformations and can be inserted into any neural network. It supports transformations like scaling, cropping, rotations, and non-rigid deformations. Main contributions:
This is a really nice way to generalize spatial transformations in a differentiable manner so the model can be trained end-to-end. Classification performance, and more importantly, qualitative results of the kind of transformations learnt on larger datasets (like ImageNet) should be evaluated.