Very Deep Convolutional Networks for Large-Scale Image Recognition · HackerPapers discussions

Very Deep Convolutional Networks for Large-Scale Image Recognition — mentioned by godelski

Wed, 02 Jun 2021 20:05:40 GMT

For more context to people, we have the universal approximation theorem for neural nets that basically says if a network is wide enough it can approximate anything (with at least 2 layers). So a lot of stuff was really wide. Then VGG[0] came out and showed that deep networks were very effective (along with other papers, things happen in unison. Leibniz and Newton). Then you get ResNets[1] with skip connections and move forward to today. Today we've started looking more at what networks are doing and where their biases lie. This is because we're running into some roadblocks with CNNs vs…

Paper and discussion history. A mention is not an endorsement.

Very Deep Convolutional Networks for Large-Scale Image Recognition — mentioned by walrus

Thu, 21 Apr 2016 13:18:05 GMT

The torrent contains the parameters for another neural network, VGG16, that this network makes use of. VGG16 is a network developed by the Visual Geometry Group at Oxford[1]. They released their parameters under CC BY-NC 4.0 to save others from spending 2-3 weeks[2] training the network. Someone else converted those parameters to work with TensorFlow[3], which is what the torrent in this repository is. I'm interested to see if neural network parameters become the new "binary blob". While in theory you could always retrain the network yourself, actually doing so takes a lot of work fiddling…

Paper and discussion history. A mention is not an endorsement.

Very Deep Convolutional Networks for Large-Scale Image Recognition — mentioned by nuclai

Thu, 10 Mar 2016 09:18:17 GMT

It's a pre-trained network on image classification dataset from 2014 called ImageNet. The network is called VGG, paper is here: http://arxiv.org/abs/1409.1556 There's no additional training apart from that. The neural network is used to extract patterns (grain/texture/style) and a separate optimization tries to reproduce them as appropriate.

Paper and discussion history. A mention is not an endorsement.

Very Deep Convolutional Networks for Large-Scale Image Recognition — mentioned by varelse

Sun, 26 Jul 2015 21:06:29 GMT

The bigger the convolution, the faster it gets because a convolution in real space is a multiplication in frequency space. It breaks even at 5x5 or so and gets dramatically better shortly thereafter. However, most of the convolutional nets in use rely on 3x3 convolutions because I guess reasons: http://arxiv.org/pdf/1409.1556.pdf (all 3x3) http://www.cs.unc.edu/~wliu/papers/GoogLeNet.pdf (3x3 and 5x5) There's probably a new Imagenet winner in this somewhere IMO...

Paper and discussion history. A mention is not an endorsement.

Very Deep Convolutional Networks for Large-Scale Image Recognition — mentioned by gcr

Tue, 21 Apr 2015 01:57:41 GMT

The current trend in convolutional neural networks seems to be moving toward more convolutions with smaller kernels. This year's second-place ILSVRC winner (VGG) is essentially a giant stack of 19 convolution layers with super tiny kernels, sandwiched between nonlinearities and pooling. "To reduce the number of parameters in such very deep networks, we use very small 3×3 filters in all convolutional layers" http://arxiv.org/pdf/1409.1556.pdf

Paper and discussion history. A mention is not an endorsement.

Very Deep Convolutional Networks for Large-Scale Image Recognition — mentioned by avallet

Sun, 08 Mar 2015 04:25:08 GMT

Hi! Author here. The blog post and source code refer to an older algorithm than the one in the demo. Currently it is using a convolutional network for prediction not dissimilar to [1] or [2]. I'm writing a paper about it, if there is interest I'll put it online :) . Thank you for the feedback on incorrectly identified characters! The algorithm is not quite perfect - 70% accuracy on a randomly chosen test set. [1]: http://arxiv.org/abs/1409.4842 [2]: http://arxiv.org/abs/1409.1556

Paper and discussion history. A mention is not an endorsement.

Very Deep Convolutional Networks for Large-Scale Image Recognition — mentioned by karpathy

Fri, 05 Sep 2014 18:19:55 GMT

Google hasn't released details about their model yet, but the VGG team in close 2nd place had a very simple and beautiful "vanilla" CovnNet model, but with more careful hyperparameter settings and training/testing protocol. In other words, the source of improvement are tweaks on the original Krizhevsky architecture from 2012, not completely new and unexpected ideas. That is not to belittle the contribution - these experiments take forever to run and require very good practices and intuitions for what to try next. Karen released the details of the model only yesterday on arXiv…

Paper and discussion history. A mention is not an endorsement.