arXiv:1409.5403cs.CV
Deformable Part Models are Convolutional Neural Networks
Abstract
Deformable part models (DPMs) and convolutional neural networks (CNNs) are two widely used tools for visual recognition. They are typically viewed as distinct approaches: DPMs are graphical models (Markov random fields), while CNNs are "black-box" non-linear classifiers. In this paper, we show that a DPM can be formulated as a CNN, thus providing a novel synthesis of the two ideas. Our construction involves unrolling the DPM inference algorithm and mapping each step to an equivalent (and at times novel) CNN layer. From this perspective, it becomes natural to replace the standard image features used in DPM with a learned feature extractor. We call the resulting model DeepPyramid DPM and experimentally validate it on PASCAL VOC. DeepPyramid DPM significantly outperforms DPMs based on histograms of oriented gradients features (HOG) and slightly outperforms a comparable version of the recently introduced R-CNN detection system, while running an order of magnitude faster.
"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…
BooglyWooView on HNParent context
Thank you for these great links. I'll add another interesting paper that carries on this emulation program: Conditional Random Fields as Recurrent Neural Networks https://arxiv.org/abs/1409.5403 I hope more fruit comes out of the fusion deep learning and graphical models.
3390778View on HNParent context