HyperMix: Out-of-Distribution Detection and Classification in Few-Shot Settings
Not on the map. Why?
Abstract (arXiv)
Out-of-distribution (OOD) detection is an important topic for real-world machine learning systems, but settings with limited in-distribution samples have been underexplored. Such few-shot OOD settings are challenging, as models have scarce opportunities to learn the data distribution before being tasked with identifying OOD samples. Indeed, we demonstrate that recent state-of-the-art OOD methods fail to outperform simple baselines in the few-shot setting. We thus propose a hypernetwork framework called HyperMix, using Mixup on the generated classifier parameters, as well as a natural out-of-episode outlier exposure technique that does not require an additional outlier dataset. We conduct experiments on CIFAR-FS and MiniImageNet, significantly outperforming other OOD methods in the few-shot regime.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 47 of its 64 references that are in the map. First posted on arXiv 22 Dec 2023.
Builds on
47 of 64 references.
References · 47
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
- 2013Intriguing properties of neural networkscited by 5,155
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
- 2016Matching Networks for One Shot Learningcited by 2,255
- 2016Adversarial examples in the physical worldcited by 1,769
- 2016Concrete Problems in AI Safetycited by 1,642
- 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
- 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
- 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
35 more
- 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
- 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
- 2016HyperNetworkscited by 1,027
- 2018Deep Anomaly Detection with Outlier Exposurecited by 942
- 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
- 2019A Closer Look at Few-shot Classificationcited by 684
- 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 463
- 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
- 2018Meta-learning with differentiable closed-form solverscited by 397
- 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
- 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
- 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
- 2020Contrastive Training for Improved Out-of-Distribution Detectioncited by 186
- 2016Person Re-identification: Past, Present and Futurecited by 181
- 2018Reducing Network Agnostophobiacited by 165
- 2019Self-Driving Cars: A Surveycited by 148
- 2019Boosting Few-Shot Visual Learning with Self-Supervisioncited by 140
- 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 136
- 2019Improved Few-Shot Visual Classificationcited by 115
- 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
- 2020Incremental Few-Shot Object Detectioncited by 102
- 2016Learning feed-forward one-shot learnerscited by 93
- 2016Low Data Drug Discovery with One-shot Learningcited by 91
- 2015Posterior calibration and exploratory analysis for natural language processing modelscited by 76
- 2018Multi-level Semantic Feature Augmentation for One-shot Learningcited by 62
- 2019Out-of-distribution Detection in Classifiers via Generationcited by 49
- 2020Self-supervised Knowledge Distillation for Few-shot Learningcited by 41
- 2019TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learningcited by 32
- 2022HyperShot: Few-Shot Learning by Kernel HyperNetworkscited by 24
- 2020Learning from Few Samples: A Surveycited by 23
- 2021Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detectioncited by 23
- 2022Few-shot Learning with Noisy Labelscited by 23
- 2022POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samplescited by 15
- 2019Toward Automatic Threat Recognition for Airport X-ray Baggage Screening with Deep Convolutional Object Detectioncited by 3
- 2021FROB: Few-shot ROBust Model for Classification and Out-of-Distribution Detectioncited by 2
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.