Generalized Cross-domain Multi-label Few-shot Learning for Chest X-rays
Not on the map. Why?
Abstract (arXiv)
Real-world application of chest X-ray abnormality classification requires dealing with several challenges: (i) limited training data; (ii) training and evaluation sets that are derived from different domains; and (iii) classes that appear during training may have partial overlap with classes of interest during evaluation. To address these challenges, we present an integrated framework called Generalized Cross-Domain Multi-Label Few-Shot Learning (GenCDML-FSL). The framework supports overlap in classes during training and evaluation, cross-domain transfer, adopts meta-learning to learn using few training samples, and assumes each chest X-ray image is either normal or associated with one or more abnormalities. Furthermore, we propose Generalized Episodic Training (GenET), a training strategy that equips models to operate with multiple challenges observed in the GenCDML-FSL scenario. Comparisons with well-established methods such as transfer learning, hybrid transfer learning, and multi-label meta-learning on multiple datasets show the superiority of our approach.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 41 of its 70 references that are in the map. First posted on arXiv 8 Sep 2023.
Builds on
41 of 70 references.
References · 41
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2017On Calibration of Modern Neural Networkscited by 4,860
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
- 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 969
- 2019A Closer Look at Few-shot Classificationcited by 679
- 2018Albumentations: fast and flexible image augmentationscited by 558
- 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
- 2021Big Self-Supervised Models Advance Medical Image Classificationcited by 320
- 2019PadChest: A large chest x-ray image dataset with multi-label annotated reportscited by 308
- 2019A Baseline for Few-Shot Image Classificationcited by 298
- 2020A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promisescited by 230
29 more
- 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
- 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
- 2016An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wildcited by 146
- 2019Feature-Critic Networks for Heterogeneous Domain Generalizationcited by 130
- 2022Learning from Few Examples: A Summary of Approaches to Few-Shot Learningcited by 86
- 2021Self-Supervised Pretraining Improves Self-Supervised Pretrainingcited by 81
- 2021Cross-domain Few-shot Learning with Task-specific Adapterscited by 79
- 2021Cross-Domain Few-Shot Classification via Adversarial Task Augmentationcited by 63
- 2020On the limits of cross-domain generalization in automated X-ray predictioncited by 61
- 2022What Makes Transfer Learning Work For Medical Images: Feature Reuse & Other Factorscited by 61
- 2021CheXtransfer: Performance and Parameter Efficiency of ImageNet Models for Chest X-Ray Interpretationcited by 57
- 2021MedAug: Contrastive learning leveraging patient metadata improves representations for chest X-ray interpretationcited by 52
- 2021Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencodercited by 51
- 2021Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Datacited by 48
- 2021Balanced-MixUp for Highly Imbalanced Medical Image Classificationcited by 46
- 2022Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Studycited by 45
- 2019LaSO: Label-Set Operations networks for multi-label few-shot learningcited by 38
- 2022Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficultycited by 37
- 2021Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgettingcited by 33
- 2019Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learningcited by 29
- 2021Relational Subsets Knowledge Distillation for Long-tailed Retinal Diseases Recognitioncited by 27
- 2021Meta-Learning for Multi-Label Few-Shot Classificationcited by 21
- 2022Cross-Domain Video Anomaly Detection without Target Domain Adaptationcited by 20
- 2021Self-supervised deep convolutional neural network for chest X-ray classificationcited by 16
- 2022TGDM: Target Guided Dynamic Mixup for Cross-Domain Few-Shot Learningcited by 16
- 2021Two Sides of Meta-Learning Evaluation: In vs. Out of Distributioncited by 9
- 2021Recur, Attend or Convolve? On Whether Temporal Modeling Matters for Cross-Domain Robustness in Action Recognitioncited by 7
- 2022Few-Shot Learning of Compact Models via Task-Specific Meta Distillationcited by 5
- 2022Can we Adopt Self-supervised Pretraining for Chest X-Rays?cited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.