Week 3 #

Topic: Semi-Supervised Learning based on Pseudo-labeling

Keynote Speaker: Shengjie Niu

Time: Jul 5, 19:30 - 21:30 pm

Venue: Business Hall 3, 314 (SUSTech)

Online Link: TencentMeeting

Compendium #

Material #

I. Weekly Slide form Shengjie Niu.

II. Source code of slide from Overleaf.

III. Some tutorials for Semi-supervised Learning:

• Kihyuk Sohn et al. Fixmatch: Simplifying semi-supervised learning with consistency and confidence..

• Awesome Semi-supervised Learning, GitHub.

• Lil’s Log, Learning with not Enough Data Part 1: Semi-Supervised Learning.

• Y Wang et al, USB: A Unified Semi-supervised Learning Benchmark for Classification.

References #

1. Kihyuk Sohn et al. Fixmatch: Simplifying semi-supervised learning with consistency and confidence..

2. Hyuck Lee et al, ABC: Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning.

3. Youngtaek Oh et al, DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning.

4. Zhengfeng Lai et al, Smoothed Adaptive Weighting for Imbalanced Semi-Supervised Learning: Improve Reliability Against Unknown Distribution Data.

5. Qing Yu et al, Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learning.

6. Lan-Zhe Guo et al, Safe Deep Semi-Supervised Learning for Unseen-Class Unlabeled Data.

7. Kuniaki Saito et al, OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers.

8. Bowen Zhang et al, FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling.

9. Yidong Wang et al, FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning.

10. Hao Chen et al, SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning.