# All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training

arXiv: https://arxiv.org/abs/2104.05248 · HTML: https://mlsanity.com/paper/2104.05248/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 45 references that are in the map.
- First posted on arXiv 12 Apr 2021.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning](https://mlsanity.com/paper/1606.04586/) (2016)
- [ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring](https://mlsanity.com/paper/1911.09785/) (2019)
- [Label Propagation for Deep Semi-supervised Learning](https://mlsanity.com/paper/1904.04717/) (2019)
- [Feature Generating Networks for Zero-Shot Learning](https://mlsanity.com/paper/1712.00981/) (2017)
- [Zero-Shot Learning -- The Good, the Bad and the Ugly](https://mlsanity.com/paper/1703.04394/) (2017)
- [Interpolation Consistency Training for Semi-Supervised Learning](https://mlsanity.com/paper/1903.03825/) (2019)
- [Semi-Supervised Learning with Ladder Networks](https://mlsanity.com/paper/1507.02672/) (2015)
- [Semantic Autoencoder for Zero-Shot Learning](https://mlsanity.com/paper/1704.08345/) (2017)
- [FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning](https://mlsanity.com/paper/2007.08505/) (2020)
- [Learning Robust Visual-Semantic Embeddings](https://mlsanity.com/paper/1703.05908/) (2017)
- [Milking CowMask for Semi-Supervised Image Classification](https://mlsanity.com/paper/2003.12022/) (2020)
- [An Ensemble Method to Produce High-Quality Word Embeddings (2016)](https://mlsanity.com/paper/1604.01692/) (2016)

## Built on by (most cited first, 30 of 32)

- [Class-Aware Contrastive Semi-Supervised Learning](https://mlsanity.com/paper/2203.02261/) (2022)
- [Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization](https://mlsanity.com/paper/2210.04388/) (2022)
- [Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data](https://mlsanity.com/paper/2303.11066/) (2023)
- [NP-Match: When Neural Processes meet Semi-Supervised Learning](https://mlsanity.com/paper/2207.01066/) (2022)
- [Semi-supervised learning made simple with self-supervised clustering](https://mlsanity.com/paper/2306.07483/) (2023)
- [Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning](https://mlsanity.com/paper/2308.06777/) (2023)
- [FisherMatch: Semi-Supervised Rotation Regression via Entropy-based Filtering](https://mlsanity.com/paper/2203.15765/) (2022)
- [ProtoCon: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learning](https://mlsanity.com/paper/2303.13556/) (2023)
- [RESMatch: Referring Expression Segmentation in a Semi-Supervised Manner](https://mlsanity.com/paper/2402.05589/) (2024)
- [CGMatch: A Different Perspective of Semi-supervised Learning](https://mlsanity.com/paper/2503.02231/) (2025)
- [RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data](https://mlsanity.com/paper/2302.14483/) (2023)
- [DoubleMatch: Improving Semi-Supervised Learning with Self-Supervision](https://mlsanity.com/paper/2205.05575/) (2022)
- [RelationMatch: Matching In-batch Relationships for Semi-supervised Learning](https://mlsanity.com/paper/2305.10397/) (2023)
- [MultiMatch: Multi-task Learning for Semi-supervised Domain Generalization](https://mlsanity.com/paper/2208.05853/) (2022)
- [Roll With the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning](https://mlsanity.com/paper/2312.12237/) (2023)
- [SEAL: Simultaneous Label Hierarchy Exploration And Learning](https://mlsanity.com/paper/2304.13374/) (2023)
- [OTMatch: Improving Semi-Supervised Learning with Optimal Transport](https://mlsanity.com/paper/2310.17455/) (2023)
- [Boosting Semi-Supervised Learning with Contrastive Complementary Labeling](https://mlsanity.com/paper/2212.06643/) (2022)
- [NP-SemiSeg: When Neural Processes meet Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2308.02866/) (2023)
- [Pseudo-Labeling Based Practical Semi-Supervised Meta-Training for Few-Shot Learning](https://mlsanity.com/paper/2207.06817/) (2022)
- [Learning from Crowds with Sparse and Imbalanced Annotations](https://mlsanity.com/paper/2107.05039/) (2021)
- [Augmentation Learning for Semi-Supervised Classification](https://mlsanity.com/paper/2208.01956/) (2022)
- [Semi-Supervised Unconstrained Head Pose Estimation in the Wild](https://mlsanity.com/paper/2404.02544/) (2024)
- [An Action Is Worth Multiple Words: Handling Ambiguity in Action Recognition](https://mlsanity.com/paper/2210.04933/) (2022)
- [LAVA: Label-efficient Visual Learning and Adaptation](https://mlsanity.com/paper/2210.10317/) (2022)
- [NorMatch: Matching Normalizing Flows with Discriminative Classifiers for Semi-Supervised Learning](https://mlsanity.com/paper/2211.09593/) (2022)
- [NP-Match: Towards a New Probabilistic Model for Semi-Supervised Learning](https://mlsanity.com/paper/2301.13569/) (2023)
- [Pushing the Envelope for Depth-Based Semi-Supervised 3D Hand Pose Estimation with Consistency Training](https://mlsanity.com/paper/2303.15147/) (2023)
- [Towards Self-Adaptive Pseudo-Label Filtering for Semi-Supervised Learning](https://mlsanity.com/paper/2309.09774/) (2023)
- [Clue Me In: Semi-Supervised FGVC with Out-of-Distribution Data](https://mlsanity.com/paper/2112.02825/) (2021)

## Abstract (arXiv)

Pseudo-labeling is a key component in semi-supervised learning (SSL). It relies on iteratively using the model to generate artificial labels for the unlabeled data to train against. A common property among its various methods is that they only rely on the model's prediction to make labeling decisions without considering any prior knowledge about the visual similarity among the classes. In this paper, we demonstrate that this degrades the quality of pseudo-labeling as it poorly represents visually similar classes in the pool of pseudo-labeled data. We propose SemCo, a method which leverages label semantics and co-training to address this problem. We train two classifiers with two different views of the class labels: one classifier uses the one-hot view of the labels and disregards any potential similarity among the classes, while the other uses a distributed view of the labels and groups potentially similar classes together. We then co-train the two classifiers to learn based on their disagreements. We show that our method achieves state-of-the-art performance across various SSL tasks including 5.6% accuracy improvement on Mini-ImageNet dataset with 1000 labeled examples. We also show that our method requires smaller batch size and fewer training iterations to reach its best performance. We make our code available at https://github.com/islam-nassar/semco.