Awesome Mixup Methods for Self- and Semi-supervised Learning¶
We summarize mixup methods proposed for self- and semi-supervised visual representation learning. We are working a survey of mixup methods. Current list is on updating.
Mixup Methods for Self-supervised Learning¶
MixCo, [NIPSW 2020] [code] MixCo: Mix-up Contrastive Learning for Visual Representation.
MoCHi, [NIPS 2020] [code] Hard Negative Mixing for Contrastive Learning.
i-Mix, [ICLR 2021] [code] i-Mix A Domain-Agnostic Strategy for Contrastive Representation Learning.
Un-Mix, [AAAI 2022] [code] Un-Mix: Rethinking Image Mixtures for Unsupervised Visual Representation.
BSIM, [Arxiv 2020] Beyond Single Instance Multi-view Unsupervised Representation Learning.
FT, [ICCV 2021] [code] Improving Contrastive Learning by Visualizing Feature Transformation.
m-Mix, [Arxiv 2021] m-mix: Generating hard negatives via multiple samples mixing for contrastive learning.
PCEA, [OpenReview 2021] Piecing and Chipping: An effective solution for the information-erasing view generation in Self-supervised Learning.
SAMix, [Arxiv 2021] [code] Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup.
MixSiam, [OpenReview 2021] MixSiam: A Mixture-based Approach to Self-supervised Representation Learning.
MixSSL, [ICME 2021] Mix-up Self-Supervised Learning for Contrast-agnostic Applications.
CLIM, [BMVC 2021] Center-wise Local Image Mixture For Contrastive Representation Learning.
Mixup Methods for Semi-supervised Learning¶
MixMatch, [NIPS 2019] [code] MixMatch: A Holistic Approach to Semi-Supervised Learning.
ReMixMatch, [ICLR 2020] [code] ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring.
Core-Tuning, [NIPS 2021] [code] Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning.
DFixMatch, [Arxiv 2022] [code] Decoupled Mixup for Data-efficient Learning.
Contribution¶
Feel free to send pull requests to add more links! Current contributors include: Siyuan Li (@Lupin1998) and Zicheng Liu (@pone7).