[ekelsen]

Nice results! But why are people still reporting benchmark results on VGG? Does anybody actually use this network anymore?

Better would be mobilenets or efficientNets or NFNets or vision transformers or almost anything that's come out in the 8 years since VGG was published (great work it was at the time!).

[plonk]

> Does anybody actually use this network anymore?

Why not? It's still good for simple classification tasks. We use it as an encoder for a segmentation model in some cases. Most ResNet variants are much heavier.

[jph00]

I don't think that's true - have a look at this analysis here:

https://www.kaggle.com/code/jhoward/which-image-models-are-b...

Those slow and inaccurate models at the bottom of the graph are the VGG models. A resnet34 is faster and more accurate than any VGG model. And there are better options now -- for example resnet34d is as fast as resnet34, and more accurate. And then convnext is dramatically better still.

[YetAnotherNick]

> ResNet > VGG: ResNet-50 is faster than VGG-16 and more accurate than VGG-19 (7.02 vs 9.0); ResNet-101 is about the same speed as VGG-19 but much more accurate than VGG-16 (6.21 vs 9.0).

https://github.com/jcjohnson/cnn-benchmarks#:~:text=ResNet%2....

[p1esk]

why are people still reporting benchmark results on VGG?

Probably because it makes the hardware look good.

[0-_-0]

This is the right answer. Efficient networks like EfficientNet are much harder to accelerate in HW.

[DSingularity]

No. Because it is a way to compare performance. That’s all. Just convenience.

[jorgemf]

Probably because it will be impossible to compare with old results. If every year the community chooses a different model, how are you going to compare results year over year?

[ekelsen]

The numbers are relative speedups, not absolute numbers that can be compared with any prior results, so I don't really see how this matters.

[jorgemf]

You need something constant, either the model or the hardware, otherwise you cannot have those relative numbers. And you usually want to have a trend. See my other reply

[learndeeply]

ResNets have been around for 7 years...

[jorgemf]

It doesn't matter. Deep learning have been mainstream for only 10 years. MNIST is a dataset from 1998 and it is still being used in research papers. The most important thing is to have a constant baseline, and ResNets are a baseline.

Think about changing the model every other year: - 2015: ResNet trained in Nvidia k80 - 2017: Inception trained in Nvidia 1080 ti - 2019: Transformer trained in Nvidia V100 - 2021: GTP-3 trained in a cluster

Now you have your new fancy algorithm X and an Nvidia 4090. How much better is your algorithm compared to the state of the art, and how much have you improved compared to the algorithms 5 years ago? Now you are in a nightmare and you have to run all the past algorithms in order to compare it. Or how fast is the new Nvidia card? which noone still have and nvidia has decided to give numbers based on a their own model?

[6gvONxR4sf7o]

> But why are people still reporting benchmark results on VGG?

It makes me feel like i’m missing something! Is is still used as a backbone in the same way as legacy code is everywhere, or is it something else entirely??

[sanxiyn]

VGG works better for style transfer than ResNet (this is a surprising result, but empirically true), but that's the only case I am aware of.

https://arxiv.org/abs/2104.05623

[eoerl]

actually it seems that it was because a lot of other well known models are not yet supported, missing ops in the Metal backend