i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning

By Kibok Lee, Yian Zhu, Kihyuk Sohn, Chun-Liang Li, Jinwoo Shin, Honglak Lee. 2021

134 citations recorded by the source corpus.

How researchers see this paper

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

1. Zhiqiang Shen
2. Eric P. Xing
3. Zechun Liu
4. Sung Ju Hwang
5. Zhuang Liu
6. Trevor Darrell
7. Dacheng Tao
8. Divyam Madaan

Citations in the corpus

• Representational Continuity for Unsupervised Continual Learning (2021, methodology): “, 1998), Fashion-MNIST (FMNIST) (Xiao et al., 2017), SVHN (Netzer et al., 2011) 62.37 ( ± 3.20) 38.05 ( ± 0.73) 39.18 ( ± 0.83) S I (Zenkeetal.,2017) 87.08 ( ± 0.79) 76.41 ( ± 0.81) 42.62 ( ± 1.31) 19.14 ( ± 0.91) 79.96 ( ± 2.63) 63.71 ( ± 1.36) 40.92 ( ± 1.64) 40.41 ( ± 1.71) A-GEM (Chaudhryetal.,2”
• Un-mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning (2020, background): “(iii) Differences to i -Mix [Lee et al. 2021] and MixCo [Kim et al. 2020].”