Dual Adversarial Alignment for Realistic Support-Query Shift Few-shot Learning
Not on the map. Why?
Abstract (arXiv)
Support-query shift few-shot learning aims to classify unseen examples (query set) to labeled data (support set) based on the learned embedding in a low-dimensional space under a distribution shift between the support set and the query set. However, in real-world scenarios the shifts are usually unknown and varied, making it difficult to estimate in advance. Therefore, in this paper, we propose a novel but more difficult challenge, RSQS, focusing on Realistic Support-Query Shift few-shot learning. The key feature of RSQS is that the individual samples in a meta-task are subjected to multiple distribution shifts in each meta-task. In addition, we propose a unified adversarial feature alignment method called DUal adversarial ALignment framework (DuaL) to relieve RSQS from two aspects, i.e., inter-domain bias and intra-domain variance. On the one hand, for the inter-domain bias, we corrupt the original data in advance and use the synthesized perturbed inputs to train the repairer network by minimizing distance in the feature level. On the other hand, for intra-domain variance, we proposed a generator network to synthesize hard, i.e., less similar, examples from the support set in a self-supervised manner and introduce regularized optimal transportation to derive a smooth optimal transportation plan. Lastly, a benchmark of RSQS is built with several state-of-the-art baselines among three datasets (CIFAR100, mini-ImageNet, and Tiered-Imagenet). Experiment results show that DuaL significantly outperforms the state-of-the-art methods in our benchmark.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 44 of its 68 references that are in the map. First posted on arXiv 5 Sep 2023.
Builds on
44 of 68 references.
References · 44
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2017Prototypical Networks for Few-shot Learningcited by 3,015
- 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
- 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
- 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
- 2016Matching Networks for One Shot Learningcited by 2,255
- 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
- 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
32 more
- 2017Random Erasing Data Augmentationcited by 1,239
- 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
- 2018LEAF: A Benchmark for Federated Settingscited by 792
- 2019A Closer Look at Few-shot Classificationcited by 684
- 2018Meta-Learning with Latent Embedding Optimizationcited by 476
- 2015Optimal Transport for Domain Adaptationcited by 463
- 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 463
- 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
- 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
- 2017Few-Shot Learning with Graph Neural Networkscited by 324
- 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 315
- 2019A Baseline for Few-Shot Image Classificationcited by 298
- 2017Data Augmentation Generative Adversarial Networkscited by 278
- 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 211
- 2018Low-Shot Learning from Imaginary Datacited by 181
- 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 163
- 2020Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustnesscited by 121
- 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
- 2022Learning from Few Examples: A Summary of Approaches to Few-Shot Learningcited by 86
- 2014Convolutional Neural Networks at Constrained Time Costcited by 81
- 2021Cross-domain Few-shot Learning with Task-specific Adapterscited by 80
- 2020Self-training for Few-shot Transfer Across Extreme Task Differencescited by 76
- 2019Hierarchically Structured Meta-learningcited by 68
- 2018Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networkscited by 35
- 2019Baby steps towards few-shot learning with multiple semanticscited by 29
- 2019Revisiting Fine-tuning for Few-shot Learningcited by 29
- 2022Matching Feature Sets for Few-Shot Image Classificationcited by 25
- 2019Variational Prototyping-Encoder: One-Shot Learning with Prototypical Imagescited by 22
- 2021Bridging Few-Shot Learning and Adaptation: New Challenges of Support-Query Shiftcited by 9
- 2020Cross-Domain Few-Shot Learning with Meta Fine-Tuningcited by 8
- 2021Contextual Gradient Scaling for Few-Shot Learningcited by 4
- 2022PGADA: Perturbation-Guided Adversarial Alignment for Few-shot Learning Under the Support-Query Shiftcited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.