# Boosting Few-Shot Learning With Adaptive Margin Loss

arXiv: https://arxiv.org/abs/2005.13826 · HTML: https://mlsanity.com/paper/2005.13826/

## Key facts

- Cited by 83 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2020.

## Built on by (most cited first, 30 of 83)

- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection](https://mlsanity.com/paper/2103.04612/) (2021)
- [Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions](https://mlsanity.com/paper/2105.04489/) (2021)
- [Rectifying the Shortcut Learning of Background for Few-Shot Learning](https://mlsanity.com/paper/2107.07746/) (2021)
- [Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation](https://mlsanity.com/paper/2210.04524/) (2022)
- [Orthogonal Projection Loss](https://mlsanity.com/paper/2103.14021/) (2021)
- [Black Box Few-Shot Adaptation for Vision-Language models](https://mlsanity.com/paper/2304.01752/) (2023)
- [Partner-Assisted Learning for Few-Shot Image Classification](https://mlsanity.com/paper/2109.07607/) (2021)
- [Few-Shot Object Detection: A Comprehensive Survey](https://mlsanity.com/paper/2112.11699/) (2021)
- [Semantic Prompt for Few-Shot Image Recognition](https://mlsanity.com/paper/2303.14123/) (2023)
- [Binocular Mutual Learning for Improving Few-shot Classification](https://mlsanity.com/paper/2108.12104/) (2021)
- [Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2106.00184/) (2021)
- [Prototype Guided Federated Learning of Visual Feature Representations](https://mlsanity.com/paper/2105.08982/) (2021)
- [How to Train Your MAML to Excel in Few-Shot Classification](https://mlsanity.com/paper/2106.16245/) (2021)
- [Task Discrepancy Maximization for Fine-grained Few-Shot Classification](https://mlsanity.com/paper/2207.01376/) (2022)
- [Learning to Learn from APIs: Black-Box Data-Free Meta-Learning](https://mlsanity.com/paper/2305.18413/) (2023)
- [Few-Shot Learning with a Strong Teacher](https://mlsanity.com/paper/2107.00197/) (2021)
- [SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learning](https://mlsanity.com/paper/2111.04316/) (2021)
- [Inferring Prototypes for Multi-Label Few-Shot Image Classification with Word Vector Guided Attention](https://mlsanity.com/paper/2112.01037/) (2021)
- [Simple Semantic-Aided Few-Shot Learning](https://mlsanity.com/paper/2311.18649/) (2023)
- [Aligning Visual Prototypes with BERT Embeddings for Few-Shot Learning](https://mlsanity.com/paper/2105.10195/) (2021)
- [FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning](https://mlsanity.com/paper/2310.15105/) (2023)
- [Federated Few-Shot Learning with Adversarial Learning](https://mlsanity.com/paper/2104.00365/) (2021)
- [Boosting Few-Shot Classification with View-Learnable Contrastive Learning](https://mlsanity.com/paper/2107.09242/) (2021)
- [What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data](https://mlsanity.com/paper/2106.06410/) (2021)
- [Architecture, Dataset and Model-Scale Agnostic Data-free Meta-Learning](https://mlsanity.com/paper/2303.11183/) (2023)
- [Boosting Few-Shot Learning via Attentive Feature Regularization](https://mlsanity.com/paper/2403.17025/) (2024)
- [Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition](https://mlsanity.com/paper/2209.10073/) (2022)
- [Modelling Commonsense Properties using Pre-Trained Bi-Encoders](https://mlsanity.com/paper/2210.02771/) (2022)
- [Revisiting Local Descriptor for Improved Few-Shot Classification](https://mlsanity.com/paper/2103.16009/) (2021)

## Abstract (arXiv)

Few-shot learning (FSL) has attracted increasing attention in recent years but remains challenging, due to the intrinsic difficulty in learning to generalize from a few examples. This paper proposes an adaptive margin principle to improve the generalization ability of metric-based meta-learning approaches for few-shot learning problems. Specifically, we first develop a class-relevant additive margin loss, where semantic similarity between each pair of classes is considered to separate samples in the feature embedding space from similar classes. Further, we incorporate the semantic context among all classes in a sampled training task and develop a task-relevant additive margin loss to better distinguish samples from different classes. Our adaptive margin method can be easily extended to a more realistic generalized FSL setting. Extensive experiments demonstrate that the proposed method can boost the performance of current metric-based meta-learning approaches, under both the standard FSL and generalized FSL settings.