What Do Deep CNNs Learn About Objects?
Computer Vision and Pattern Recognition
2015-04-13 v1
Abstract
Deep convolutional neural networks learn extremely powerful image representations, yet most of that power is hidden in the millions of deep-layer parameters. What exactly do these parameters represent? Recent work has started to analyse CNN representations, finding that, e.g., they are invariant to some 2D transformations Fischer et al. (2014), but are confused by particular types of image noise Nguyen et al. (2014). In this work, we delve deeper and ask: how invariant are CNNs to object-class variations caused by 3D shape, pose, and photorealism?
Cite
@article{arxiv.1504.02485,
title = {What Do Deep CNNs Learn About Objects?},
author = {Xingchao Peng and Baochen Sun and Karim Ali and Kate Saenko},
journal= {arXiv preprint arXiv:1504.02485},
year = {2015}
}
Comments
2 pages workshop paper. arXiv admin note: substantial text overlap with arXiv:1412.7122