HackerPapers

arXiv:1311.2901cs.CV

Visualizing and Understanding Convolutional Networks

Matthew D Zeiler, Rob Fergus

Abstract

Large Convolutional Network models have recently demonstrated impressive classification performance on the ImageNet benchmark. However there is no clear understanding of why they perform so well, or how they might be improved. In this paper we address both issues. We introduce a novel visualization technique that gives insight into the function of intermediate feature layers and the operation of the classifier. We also perform an ablation study to discover the performance contribution from different model layers. This enables us to find model architectures that outperform Krizhevsky \etal on the ImageNet classification benchmark. We show our ImageNet model generalizes well to other datasets: when the softmax classifier is retrained, it convincingly beats the current state-of-the-art results on Caltech-101 and Caltech-256 datasets.

arXiv comments
Journal reference
DOI
Subjects
cs.CVComputer Vision and Pattern Recognition

On Hacker News

Linked by 11 identifiable commenters in 11 comments across 11 threads, from Jan 2015 to Oct 2026. Found in 3 HN submissions from Oct 2014 to Aug 2020. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments11 threads

  1. Feature Visualization – How neural networks build understanding of images (2017) 1 comment

    • Related: The Building Blocks of Interpretability https://distill.pub/2018/building-blocks/ Activation Atlas https://distill.pub/2019/activation-atlas/ Visualizing and Understanding Convolutional Networks https://arxiv.org/pdf/1311.2901

      peter_d_shermanView on HNParent context

  2. How do neural networks learn? 1 comment

    • The 2013 Zeiler and Fergus paper also explains this based on activations during training of the network resulting in feature detection across layers. Paper : https://arxiv.org/pdf/1311.2901.pdf

      garyiskiddingView on HNParent context

  3. Decomposing language models into understandable components 1 comment

    • Some architectures are relatively well understood. Eg in CNNs, the first layers detect low level features like edges, gradients, etc. The next layer then combines these features to more complex structures like corners or circles. Next layer will combine these features to even…

      karxxmView on HNParent context

  4. Gaussian splatting is pretty cool 1 comment

    • There’s no helping the incurious, but there are indeed reams of explorations unto weights and their explanations. One of my personal favourites is Zeiler and Fergus https://arxiv.org/abs/1311.2901 Tom Zahavy’s “Greying the black box” on deep RL comes to mind too…

      bluebooView on HNParent context

  5. For AI to thrive, it must explain itself 1 comment

    • There's a pretty cool paper that visualises the different layers in a ConvNet trained on ImageNet: https://arxiv.org/pdf/1311.2901.pdf - page 4 has the layer imagery.

      mcintyre1994View on HNParent context

  6. Feature Visualization: How neural nets build up their understanding of images 1 comment
  7. Understanding deep learning requires rethinking generalization 1 comment

    • https://arxiv.org/abs/1311.2901 Check out figure 2. The network learns composition from fundamental shapes and gradients to compositional ones. It's kinda awe inspiring. Not NN specific, but some more work on explanations: https://homes.cs.washington.edu/~marcotcr/blog/lime/…

      hiddencostView on HNParent context

  8. The Difference Between AI, Machine Learning, and Deep Learning 1 comment

    • It's definitely possible to get insight into how a CNN would classify something like a stop sign. This paper does a good job of showing how CNNs learn a hierarchy of increasingly complex features to classify images: http://arxiv.org/abs/1311.2901

      augusttView on HNParent context

  9. Visualizing GoogLeNet Classes 1 comment

    • Seeing the face of a dog just means that the network has learned a good representation of dog faces. I don't think that has anything to do with the generalization ability of the network. I'm not clear on the details of this hallucination process, but this reminds me of earlier…

      sxyuanView on HNParent context

  10. Image Kernels Explained Visually 1 comment

    • A few other useful resources to play with convolutional kernels: * The linked demo really focuses only on layer 1. See Layers >=2 plotted here: http://arxiv.org/pdf/1311.2901v3.pdf * DeepViz is a nice tool: https://github.com/bruckner/deepViz * Another tool one can use to play…

      choppafaceView on HNParent context

  11. A.I. Has Grown Up and Left Home 1 comment

    • You make some pretty strong attacks on the state of the art approach to computer vision. Could you please provide citations? As someone working on neural networks, although not really on computer vision, I do not believe several of the things you said are true. > > Pornographic…

      colah3View on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.