A Simple Approach to Adversarial Robustness in Few-shot Image Classification
Not on the map. Why?
Abstract (arXiv)
Few-shot image classification, where the goal is to generalize to tasks with limited labeled data, has seen great progress over the years. However, the classifiers are vulnerable to adversarial examples, posing a question regarding their generalization capabilities. Recent works have tried to combine meta-learning approaches with adversarial training to improve the robustness of few-shot classifiers. We show that a simple transfer-learning based approach can be used to train adversarially robust few-shot classifiers. We also present a method for novel classification task based on calibrating the centroid of the few-shot category towards the base classes. We show that standard adversarial training on base categories along with calibrated centroid-based classifier in the novel categories, outperforms or is on-par with state-of-the-art advanced methods on standard benchmarks for few-shot learning. Our method is simple, easy to scale, and with little effort can lead to robust few-shot classifiers. Code is available here: urlhttps://github.com/UCDvision/Simplefewshot.git
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 53 of its 64 references that are in the map. First posted on arXiv 11 Apr 2022.
Builds on
53 of 64 references.
References · 53
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2016Densely Connected Convolutional Networkscited by 6,720
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2013Intriguing properties of neural networkscited by 5,155
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
- 2016Wide Residual Networkscited by 3,070
- 2017Prototypical Networks for Few-shot Learningcited by 3,015
- 2016Matching Networks for One Shot Learningcited by 2,255
38 more
- 2016Adversarial examples in the physical worldcited by 1,769
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
- 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
- 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,209
- 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
- 2018On First-Order Meta-Learning Algorithmscited by 1,018
- 2018Robustness May Be at Odds with Accuracycited by 880
- 2019A Closer Look at Few-shot Classificationcited by 684
- 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
- 2019Adversarial Training for Free!cited by 643
- 2016Learning to learn by gradient descent by gradient descentcited by 620
- 2018Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNscited by 588
- 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 567
- 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 546
- 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
- 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
- 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 328
- 2018Adversarially Robust Generalization Requires More Datacited by 318
- 2019A Baseline for Few-Shot Image Classificationcited by 298
- 2017Data Augmentation Generative Adversarial Networkscited by 278
- 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 278
- 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
- 2017Detecting Adversarial Samples from Artifactscited by 245
- 2019Towards Stable and Efficient Training of Verifiably Robust Neural Networkscited by 205
- 2018Low-Shot Learning from Imaginary Datacited by 181
- 2018Semidefinite relaxations for certifying robustness to adversarial examplescited by 179
- 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
- 2020Randomized Smoothing of All Shapes and Sizescited by 147
- 2018Scaling provable adversarial defensescited by 143
- 2016Learning feed-forward one-shot learnerscited by 93
- 2016Adversarial Examples Detection in Deep Networks with Convolutional Filter Statisticscited by 77
- 2020Learning Meta Face Recognition in Unseen Domainscited by 61
- 2020Tracking by Instance Detection: A Meta-Learning Approachcited by 61
- 2016Defensive Distillation is Not Robust to Adversarial Examplescited by 60
- 2019Few-Shot Learning with Embedded Class Models and Shot-Free Meta Trainingcited by 57
- 2018Few-Shot Learning with Metric-Agnostic Conditional Embeddingscited by 40
- 2021On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learningcited by 29
50 most cited of 53 All 53 (JSON)
Built on by
Citing papers per year: 2022: 1; 2023: 1; 2024: 1.
3 papers.