Pratik’s Pakodas 🍿

Share this post
NLP Keeps Stealing From CV 👨🏻‍🎤
pakodas.substack.com

NLP Keeps Stealing From CV 👨🏻‍🎤

Why NLP engineers shouldn’t stop learning CV

Pratik Bhavsar
Aug 19, 2020
2
Share this post
NLP Keeps Stealing From CV 👨🏻‍🎤
pakodas.substack.com

Photo by Dan-Cristian Pădureț on Unsplash

I think I committed a grave mistake of not following Computer Vision(CV) for many years. A majority of advancements in NLP actually came from CV. I am no researcher but I don’t like to be in the dark.

The thought process started when I came across this paper - SqueezeBERT: What can computer vision teach NLP about efficient neural networks.

Multihead in transformer seems like a reincarnation of more than 1 filter in CNN.

Fixed window attention has its root in text CNN and graph theory. The performance difference between full self-attention and CNN with a window of 5 is not much.

Transfer learning was born when people started trying AlexNet(2012) for CIFAR dataset.

Data augmentation in NLP comes from data augmentation and corruption techniques in CV.

Residual in Transformer and LSTM come from ResNet(2015).

The idea of improving models by increasing depth came from VGG.

Triplet loss from FaceNet era is now used in making sentence transformers.

In lieu of this, I have decided to go through some CV courses in my free time.

Deep learning for Computer Vision

Advanced Computer Vision

Can you think of any other ideas borrowed from CV?

Image for post

We have a group of NLP professionals across the globe where we discuss real problems of making ML systems.

Ask me anything on ama.pratik.ai 👻

You can try ask.pratik.ai for any study material.

I am also on Medium, Twitter & LinkedIn!

Share this post
NLP Keeps Stealing From CV 👨🏻‍🎤
pakodas.substack.com
Comments

Create your profile

0 subscriptions will be displayed on your profile (edit)

Skip for now

Only paid subscribers can comment on this post

Already a paid subscriber? Sign in

Check your email

For your security, we need to re-authenticate you.

Click the link we sent to , or click here to sign in.

TopNewCommunity

No posts

Ready for more?

© 2022 Pratik
Privacy ∙ Terms ∙ Collection notice
Publish on Substack Get the app
Substack is the home for great writing