Three Towers: Flexible Contrastive Learning with Pretrained Image Models

By Jannik Kossen, Mark Collier, Basil Mustafa, Xiao Wang, Xiaohua Zhai, Lucas Beyer, Andreas Steiner, Jesse Berent, Rodolphe Jenatton, Efi Kokiopoulou. 2023

Subfields: Computer Vision and Pattern Recognition, Multimodal Learning, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Andriy Mulyar
2. Zach Nussbaum
3. Brandon Duderstadt

In Multimodal Learning

1. Andriy Mulyar
2. Zach Nussbaum
3. Brandon Duderstadt

In Representation & Self-Supervised Learning

1. Andriy Mulyar
2. Zach Nussbaum
3. Brandon Duderstadt

Citations in the corpus

• Nomic Embed Vision: Expanding the Latent Space (2024, methodology): “Three towers training (Kossen et al., 2023) presents a promising direction for remedying this.”