CNN Features off-the-shelf: an Astounding Baseline for Recognition · HackerPapers discussions

CNN Features off-the-shelf: an Astounding Baseline for Recognition — mentioned by mlucy

Thu, 14 Feb 2019 19:48:56 GMT

> Is it always good enough to take the outputs of the next-to-last layer as features? It usually doesn't matter all that much whether you take the next-to-last or the third from last, it all performs pretty similarly. If you're doing transfer to a task that's very dissimilar from the pretraining task, I think it can sometimes be helpful to take the first dense layer after the convolutional layers instead, but I can't seem to find the paper where I remember reading that, so take it with a grain of salt. > When doing quick iterations, I assume the images in the data set have been run through…

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

CNN Features off-the-shelf: an Astounding Baseline for Recognition — mentioned by mlucy

Wed, 31 Oct 2018 20:50:47 GMT

Hey! We're embedding images by feeding them through a deep neural net and using the activations of an intermediate layer as an embedding. You can read https://arxiv.org/abs/1403.6382 to learn more about this technique if you're interested. Our launch model is trained on ImageNet, which has enough variety that it usually generalizes well even when your dataset is very dissimilar to the input distribution. We're planning to train on a wider variety of image data in the future, but we wanted to get something into people's hands quickly.

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

CNN Features off-the-shelf: an Astounding Baseline for Recognition — mentioned by mlucy

Wed, 31 Oct 2018 17:48:16 GMT

We're feeding them through a deep neural network and using the activations of an intermediate layer as an embedding. You can read more about this technique in https://arxiv.org/abs/1403.6382 if you're interested.

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

CNN Features off-the-shelf: an Astounding Baseline for Recognition — HN submission

Fri, 04 Apr 2014 05:28:14 GMT

ConvNet Features off-the-shelf: an Astounding Baseline for Object Recognition

10 points; 4 discussion replies on HN. Paper and source history. A submission is not an endorsement.