0
$\begingroup$

What is the largest network (in number of params and layers) considered in the literature for image recognition/segmentation task? I am in particular interested in ResNet architectures. Any recommendation for literature is appreciated.

For natural language processing, the largest models are of order of billions, such as Megatron-LM, or DeepSeed with Zero. Is this also the case for image-classification?

$\endgroup$
0
$\begingroup$

Unet was published around 2015 and still regarded as state of the art. Since then different versions of Unet has appeared. Resnet, Squeezenet blocks can be used instead of normal convolutional blocks in Unet.

In addition to that, DeepLab currently holds top position in most of the benchmarks. But it is not ideal to train from scratch since the model is too big. Averagely one epoch of DeepLab v3+ (newest edition) takes 10 mins to train in the original implementation in Google Colab. In addition to that, mean IoU increases very slowly, and hence you will have to train for 1000s of epochs.

But in Unet, the model is very small and trains very quickly. The best thing about Unet is that it can be trained for even 30 images. I myself have used Unet for 14 images and got very good results.

$\endgroup$
0
$\begingroup$

There are many models proposed for image segmentation but I've used the U-net architecture which is basic enough for educational reading.

Some more examples can be found here

$\endgroup$
1
  • $\begingroup$ thanks! I am actually not interested in using any type of network. I am just looking for some statistic which provides an overview on the current state of the art. $\endgroup$
    – user107431
    Nov 13 '20 at 22:25

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.