Few-shot Forgery Detection via Guided Adversarial Interpolation

by   Haonan Qiu, et al.

Realistic visual media synthesis is becoming a critical societal issue with the surge of face manipulation models; new forgery approaches emerge at an unprecedented pace. Unfortunately, existing forgery detection methods suffer significant performance drops when applied to novel forgery approaches. In this work, we address the few-shot forgery detection problem by designing a comprehensive benchmark based on coverage analysis among various forgery approaches, and proposing Guided Adversarial Interpolation (GAI). Our key insight is that there exist transferable distribution characteristics among different forgery approaches with the majority and minority classes. Specifically, we enhance the discriminative ability against novel forgery approaches via adversarially interpolating the artifacts of the minority samples to the majority samples under the guidance of a teacher network. Unlike the standard re-balancing method which usually results in over-fitting to minority classes, our method simultaneously takes account of the diversity of majority information as well as the significance of minority information. Extensive experiments demonstrate that our GAI achieves state-of-the-art performances on the established few-shot forgery detection benchmark. Notably, our method is also validated to be robust to choices of majority and minority forgery approaches.


page 1

page 3

page 4

page 6

page 7

page 9

page 12


MINI: Mining Implicit Novel Instances for Few-Shot Object Detection

Learning from a few training samples is a desirable ability of an object...

Few-Shot Learning with Intra-Class Knowledge Transfer

We consider the few-shot classification task with an unbalanced dataset,...

Unsupervised Evaluation of Out-of-distribution Detection: A Data-centric Perspective

Out-of-distribution (OOD) detection methods assume that they have test g...

Few-Shot Object Detection via Synthetic Features with Optimal Transport

Few-shot object detection aims to simultaneously localize and classify t...

Confusable Learning for Large-class Few-Shot Classification

Few-shot image classification is challenging due to the lack of ample sa...

FS-BAN: Born-Again Networks for Domain Generalization Few-Shot Classification

Conventional Few-shot classification (FSC) aims to recognize samples fro...

Please sign up or login with your details

Forgot password? Click here to reset