105 citations · 261 across the 26 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.LG2022★ 4 cited
Drawing out of Distribution with Neuro-Symbolic Generative Models
Yichao Liang, Joshua B. Tenenbaum, Tuan Anh Le +1
Learning general-purpose representations from perceptual inputs is a hallmark of human intelligence. For example, people can write out numbers or characters, or even draw doodles,…
cs.CV2022★ 14 cited
Adversarial Masking for Self-Supervised Learning
Yuge Shi, N. Siddharth, Philip H. S. Torr +1
We propose ADIOS, a masked image model (MIM) framework for self-supervised learning, which simultaneously learns a masking function and an image encoder using an adversarial object…