AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

Defensive Few-shot Learning

Wenbin Li, Lei Wang, Xingxing Zhang, Lei Qi, Jing Huo, Yang Gao, Jiebo Luo

TPAMI 2022 · Adversarial robustness and security › Certified and empirical robustness · approach: Attack evaluation and defense critique · 14 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add adversarial training to DN4 (ablation)DN4 · miniImageNet 5-way 5-shot (eps=0.01)adversarial accuracy: 21.54 -> 38.19Improved
add episodic training to adversarially trained DN4 (ET) (ablation)DN4+AT · miniImageNet 5-way 5-shot (eps=0.01)adversarial accuracy: 38.19 -> 54.97Improved
add episodic training to adversarially trained DN4 (ET), clean accuracy (ablation)DN4+AT · miniImageNet 5-way 5-shotclean accuracy: 52.12 -> 71.54Improved
add adversarial training to episodically trained DN4 (ablation)DN4+Ep · miniImageNet 5-way 5-shot (eps=0.01)adversarial accuracy: 8.65 -> 54.97Improved
add episodic training to plain DN4 without AT (ablation)DN4 · miniImageNet 5-way 5-shot (eps=0.01)adversarial accuracy: 21.54 -> 8.65Hurt
add episodic training to plain DN4 without AT, clean accuracy (ablation)DN4 · miniImageNet 5-way 5-shotclean accuracy: 57.74 -> 70.39Improved
apply ET to ProtoNet+AT (ablation)ProtoNet · miniImageNet 5-way 5-shotclean accuracy: 54.61 -> 63.70Improved
apply ET to DeepEMD+AT (ablation)DeepEMD · miniImageNet 5-way 5-shotclean accuracy: 55.09 -> 60.20Improved
use DN4 classifier instead of ProtoNet within DFSL-ATDFSL framework · miniImageNet 5-way 5-shot (eps=0.01)adversarial accuracy: 39.05 -> 54.97Improved
add SKL prediction-wise consistency to DFSL-DN4-ATDFSL-DN4 · miniImageNet 5-way 5-shot (eps=0.01)adversarial accuracy: 54.97 -> 62.68Improved
add TCD feature-wise consistency to DFSL-DN4-ATDFSL-DN4 · tieredImageNet 5-way 5-shot (eps=0.01)adversarial accuracy: 53.73 -> 63.67Improved
use SKL instead of ALPDFSL-DN4 · CIFAR-100 5-way 5-shot (eps=0.01)adversarial accuracy: 40.59 -> 44.79Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy