Inverse Compositional Spatial Transformer Networks — mentioned by BooglyWoo

Fri, 28 Apr 2017 09:18:00 GMT

"Classical" CV and deep-learning CV needn't be opposing one another. There are several cases in which the classical approach is emulated by deep networks - implementing the same carefully thought-out pipelines but in a way that leverages representations learned from huge datasets (which are undeniably very powerful). Some examples are: * Bags of convolutional features for scalable instance search https://arxiv.org/pdf/1604.04653.pdf This paper treats each 'pixel' of a CNN activation tensor as a local descriptor, clusters them, and describes an image as a bag-of-visual-words histogram. *…

Paper and discussion history. A mention is not an endorsement.

Inverse Compositional Spatial Transformer Networks · HackerPapers discussions

Inverse Compositional Spatial Transformer Networks — mentioned by BooglyWoo