Contrastive Clustering with SwAV

Sdílet
Vložit
  • čas přidán 29. 08. 2024

Komentáře • 18

  • @connor-shorten
    @connor-shorten  Před 4 lety

    2:10 Motivation Contrastive vs. Generative self-supervised learning
    3:02 Contrastive Learning Progress
    4:25 Instance Discrimination
    7:42 Criticism of Instance Disrimination (I think these are really interesting issues raised)
    9:02 Contrasive Instance Learning vs. Cluster Prediction
    10:47 Contrast with Prototypical Contrastive Learning
    11:42 Motivation of Online Clustering
    14:16 Multi-Crop Augmentation
    14:47 Results
    16:36 I’d like to see more of this and less linear evaluation of representations (especially from big labs like Facebook)

  • @Adam-xy6es
    @Adam-xy6es Před 4 lety +11

    You are doing god's work mate.

  • @virajdattkohir4767
    @virajdattkohir4767 Před 4 lety +3

    Wow, mind-blowing. U keep generating high quality content faster than one can consume spanning many sub domains, great commitment and fantastic explanations.

  • @juanmanuelcirotorres6155
    @juanmanuelcirotorres6155 Před 3 lety +1

    Man you literally saved my presentation, again haha, thanks

  • @123dongwan
    @123dongwan Před 4 lety

    Thanks for the summary!

  • @BlakeEdwards333
    @BlakeEdwards333 Před 4 lety +1

    Been watching since day one Henry because of your unique and great coverage of SOTA topics. Keep it up and thank you!!!

  • @kritiohri558
    @kritiohri558 Před 3 lety +2

    Hello, I love your videos..a normal student trying to understand the latest and greatest research happening. I wanted to ask if these algorithms can be used for medical images?

    • @connor-shorten
      @connor-shorten  Před 3 lety +1

      Definitely! See - "MoCo Pretraining Improves Representation and Transferability of Chest X-ray Models"! Goodluck with your research!

  • @bayesianlee6447
    @bayesianlee6447 Před 4 lety +1

    Can make vid of ALAE if u have interest on generative models? I'm still having hard time to understand this paper.
    It's first try to use latent space autoencoder and results are amazing

    • @connor-shorten
      @connor-shorten  Před 4 lety +1

      Haha I was scared off by the double integral! I have a poor understanding of how they marginalize over latent variables for models like that, I've been working through Chapter 19 of Bengio, Goodfellow, and Courville's deep learning book to get a better sense of it. I think you might find it interesting as well, www.deeplearningbook.org/

  • @weitaotang5702
    @weitaotang5702 Před 3 lety

    I come here to find how is Q calculated, and learned it's in the appendix :\