Self supervised learning and foundational models

why is SSL necessary?

  1. representation learning
    • raw data → representations
      • generalize across multiple downstream tasks
      • compact rep (output dim << input dim)
      • robust - invariant to noise
    • ex - pretraining AlexNet on ImageNet for img classification, but can be later used for segmentation!

visual common sense tasks

contrastive learning

self-distillation

generative reconstruction

beyond images - point clouds, audio, and video

foundational models

applications of SSL

202609141609