Self Supervised Learning is Taking Off

 The cutting edge of deep learning research in self-supervised learning algorithms is taking off.  Self supervised being a neural net that learns from the data in the model, not from supervised labels or other pattern match-ups tagged by humans.  

And in some sense it's really all about data augmentation.  And we move from thinking about data augmentation as just a way to endlessly expand our model's data, to thinking about it as a way to introduce perceptual clustering of the data in our model so that the training process can manipulate it's energy surface to correspond to the natural perceptual classes in the data (doing this with human intervention).  Actually the human intervention is the human designing the correct perceptual augmentation.

SwAV is the latest paper from FAIR to generate state of the art results in self-supervised learning.  With exciting potential for an alternative approach to transfer learning (alternative to a ResNet model (or equivalent)).

Here's a more relaxed conversation with Mathilde Caron (paper author in the first presentation) on Machine Learning Street Talk.

1.  Yannic mentions how disappointing it is to not be able to load the full data set into memory to train the clustering.  But is that really true?  Stochastic gradient descent works in some sense because of the batch processing introducing randomization into the gradient descent. Perhaps's something similar is going on here with the clustering, where working in batches serves as a benefit in some sense.

2. I found it interesting that Sayak and Ayush mentioned how much more difficult it was to do the data augmentation in Tensorflow (as opposed to PyTorch).

About those referenced papers

"SwaV: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments" here.

"Unsupervised Visual Representation Learning with SwAV" here.

Here's another take on all of this on a slightly different perspective from the gang at Machine Learning Street Talk. Stepping back for a bigger picture.  A very accessible but at the same time surprisingly thoughtful and fascinating discussion.

About those referenced papers

"Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth" here.

"What's in a Loss Function for Image Classification?" here.

"A Simple Framework for Contrastive Learning of Visual Representations" here.

"Big Self-Supervised Models are Strong Semi-Supervised Learners" here.


Popular posts from this blog

Pix2Pix: a GAN architecture for image to image transformation

CycleGAN: a GAN architecture for learning unpaired image to image transformations

Smart Fabrics