# FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning

arXiv: https://arxiv.org/abs/2007.08505 · HTML: https://mlsanity.com/paper/2007.08505/

## Key facts

- Cited by 57 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jul 2020.

## Built on by (most cited first, 30 of 57)

- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2208.09910/) (2022)
- [Image Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2204.08610/) (2022)
- [Bootstrapping Semantic Segmentation with Regional Contrast](https://mlsanity.com/paper/2104.04465/) (2021)
- [UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2410.10777/) (2024)
- [DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2106.05682/) (2021)
- [SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving](https://mlsanity.com/paper/2106.11118/) (2021)
- [A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classification](https://mlsanity.com/paper/2104.00679/) (2021)
- [Revisiting Consistency Regularization for Semi-Supervised Learning](https://mlsanity.com/paper/2112.05825/) (2021)
- [All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training](https://mlsanity.com/paper/2104.05248/) (2021)
- [Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning](https://mlsanity.com/paper/2103.10211/) (2021)
- [Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2308.12595/) (2023)
- [Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition](https://mlsanity.com/paper/2206.04790/) (2022)
- [Multimodal Semi-Supervised Learning for 3D Objects](https://mlsanity.com/paper/2110.11601/) (2021)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [Learning Representational Invariances for Data-Efficient Action Recognition](https://mlsanity.com/paper/2103.16565/) (2021)
- [Semi-Supervised Learning of Semantic Correspondence with Pseudo-Labels](https://mlsanity.com/paper/2203.16038/) (2022)
- [A Simple Baseline for Low-Budget Active Learning](https://mlsanity.com/paper/2110.12033/) (2021)
- [Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions](https://mlsanity.com/paper/2202.11423/) (2022)
- [Learning to Extract Building Footprints from Off-Nadir Aerial Images](https://mlsanity.com/paper/2204.13637/) (2022)
- [ProtoCon: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learning](https://mlsanity.com/paper/2303.13556/) (2023)
- [Boosting Semi-Supervised Learning by bridging high and low-confidence predictions](https://mlsanity.com/paper/2308.07509/) (2023)
- [SIOD: Single Instance Annotated Per Category Per Image for Object Detection](https://mlsanity.com/paper/2203.15353/) (2022)
- [RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data](https://mlsanity.com/paper/2302.14483/) (2023)
- [HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning](https://mlsanity.com/paper/2305.16295/) (2023)
- [Better Pseudo-label: Joint Domain-aware Label and Dual-classifier for Semi-supervised Domain Generalization](https://mlsanity.com/paper/2110.04820/) (2021)
- [Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with Proper Calibration](https://mlsanity.com/paper/2306.04621/) (2023)
- [An Empirical Study and Analysis on Open-Set Semi-Supervised Learning](https://mlsanity.com/paper/2101.08237/) (2021)
- [Boosting Semi-Supervised Learning with Contrastive Complementary Labeling](https://mlsanity.com/paper/2212.06643/) (2022)
- [Semi-supervised Object Detection: A Survey on Recent Research and Progress](https://mlsanity.com/paper/2306.14106/) (2023)

## Abstract (arXiv)

Recent state-of-the-art semi-supervised learning (SSL) methods use a combination of image-based transformations and consistency regularization as core components. Such methods, however, are limited to simple transformations such as traditional data augmentation or convex combinations of two images. In this paper, we propose a novel learned feature-based refinement and augmentation method that produces a varied set of complex transformations. Importantly, these transformations also use information from both within-class and across-class prototypical representations that we extract through clustering. We use features already computed across iterations by storing them in a memory bank, obviating the need for significant extra computation. These transformations, combined with traditional image-based augmentation, are then used as part of the consistency-based regularization loss. We demonstrate that our method is comparable to current state of art for smaller datasets (CIFAR-10 and SVHN) while being able to scale up to larger datasets such as CIFAR-100 and mini-Imagenet where we achieve significant gains over the state of art (textite.g., absolute 17.44% gain on mini-ImageNet). We further test our method on DomainNet, demonstrating better robustness to out-of-domain unlabeled data, and perform rigorous ablations and analysis to validate the method.