Rethinking the Inception Architecture for Computer Vision · HackerPapers discussions

Rethinking the Inception Architecture for Computer Vision — mentioned by vincentchu

Wed, 05 Apr 2017 17:37:40 GMT

The latest deep learning models are indeed quite large. For comparison, Inception clocks in at "only" 5M parameters, itself a 12x reduction over AlexNet (60M) and VGGNet (180M)! (source: https://arxiv.org/abs/1512.00567) A further point is that even if the model has relatively few parameters, there are advantages to having more memory--- namely, you can do inference on larger batch sizes in one go.

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

Rethinking the Inception Architecture for Computer Vision — mentioned by dlubarov

Thu, 18 Aug 2016 23:25:03 GMT

> It's 2016 and our best of the best image recognition algorithms can't even tell a zebra and a sofa in a zebra print apart. State of the art offline CNNs have been doing classification quite well recently, arguably better than humans. See the Inception-v3 paper: http://arxiv.org/pdf/1512.00567v3.pdf

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

Rethinking the Inception Architecture for Computer Vision — mentioned by daveguy

Fri, 01 Jul 2016 01:42:08 GMT

Looking up info on the inception architecture. Here is a paper if others are wondering: http://arxiv.org/pdf/1512.00567v3 From late 2015, so I guess the most up to date info? It only mentions v2. Is there a paper for v3? Edit: Sure enough v3 is right there. I saw the early focus on v2 and jumped to the big dumb assumption that v3 wasn't in there.

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

Rethinking the Inception Architecture for Computer Vision — mentioned by nl

Wed, 13 Jan 2016 05:16:32 GMT

[1] is a Google-authored demo running Inception-v3[2] (about twice as accurate as VGG) on Android phones. I don't know how many parameters Inception v3 has, but I know Google considers it more efficient than VGG ("Although our network is 42 layers deep, our computation cost is only about 2.5 higher than that of GoogLeNet and it is still much more efficient than VGGNet".) Yes, being able to run big networks is great. But ultimately it's what you do with it, and a 3% error rate on ImageNet is a pretty compelling argument that size isn't the only factor. [1]…

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

Rethinking the Inception Architecture for Computer Vision — HN submission

Fri, 04 Dec 2015 04:35:11 GMT

Rethinking the Inception Architecture for Computer Vision

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Rethinking the Inception Architecture for Computer Vision — HN submission

Thu, 03 Dec 2015 03:58:22 GMT

Rethinking the Inception Architecture for Computer Vision

2 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.