Corpus ID: 15106200

What Do Deep CNNs Learn About Objects?

  title={What Do Deep CNNs Learn About Objects?},
  author={Xingchao Peng and Baochen Sun and Karim Ali and Kate Saenko},
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… Expand
2 Citations
Deep CORAL: Correlation Alignment for Deep Domain Adaptation
  • 783
  • PDF
Deep Unsupervised Convolutional Domain Adaptation
  • 48
  • PDF


Exploring Invariances in Deep Convolutional Neural Networks Using Synthetic Images
  • 48
  • PDF
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
  • 1,910
  • PDF
ImageNet classification with deep convolutional neural networks
  • 62,892
  • PDF
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
  • 13,562
  • PDF
Descriptor Matching with Convolutional Neural Networks: a Comparison to SIFT
  • 228
  • PDF