Digging Deep into the layers of CNNs: In Search of How CNNs Achieve View Invariance
arXiv:1508.01983
Abstract
This paper is focused on studying the view-manifold structure in the feature spaces implied by the different layers of Convolutional Neural Networks (CNN). There are several questions that this paper aims to answer: Does the learned CNN representation achieve viewpoint invariance? How does it achieve viewpoint invariance? Is it achieved by collapsing the view manifolds, or separating them while preserving them? At which layer is view invariance achieved? How can the structure of the view manifold at each layer of a deep convolutional neural network be quantified experimentally? How does fine-tuning of a pre-trained CNN on a multi-view dataset affect the representation at each layer of the network? In order to answer these questions we propose a methodology to quantify the deformation and degeneracy of view manifolds in CNN layers. We apply this methodology and report interesting results in this paper that answer the aforementioned questions.
arXiv commentThis paper accepted in ICLR 2016 main conference
References in corpus (7)
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
- Return of the Devil in the Details: Delving Deep into Convolutional Nets
- CNN Features off-the-shelf: an Astounding Baseline for Recognition
- Rich feature hierarchies for accurate object detection and semantic segmentation
- Convolutional Models for Joint Object Categorization and Pose Estimation
- Factorization of View-Object Manifolds for Joint Object Recognition and Pose Estimation