A Simple Approach to Adversarial Robustness in Few-shot Image Classification

04/11/2022
by   Akshayvarun Subramanya, et al.
3

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: <https://github.com/UCDvision/Simple_few_shot.git>

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/02/2019

Robust Few-Shot Learning with Adversarially Queried Meta-Learners

Previous work on adversarially robust neural networks requires large tra...
research
11/03/2022

Robust Few-shot Learning Without Using any Adversarial Samples

The high cost of acquiring and annotating samples has made the `few-shot...
research
10/06/2021

On the Importance of Firth Bias Reduction in Few-Shot Classification

Learning accurate classifiers for novel categories from very few example...
research
01/30/2023

Anchor-Based Adversarially Robust Zero-Shot Learning Driven by Language

Deep neural networks are vulnerable to adversarial attacks. We consider ...
research
04/15/2022

Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference

Few-shot learning (FSL) is an important and topical problem in computer ...
research
12/23/2021

Dual Path Structural Contrastive Embeddings for Learning Novel Objects

Learning novel classes from a very few labeled samples has attracted inc...
research
01/23/2012

A probabilistic methodology for multilabel classification

Multilabel classification is a relatively recent subfield of machine lea...

Please sign up or login with your details

Forgot password? Click here to reset