.png){kind=icon}
返回
Learning Patch-Channel Correspondence for Interpretable Face Forgery Detection
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2023.3246793.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Beyond high accuracy, good interpretability is very critical to deploy a face forgery detection model for visual content analysis. In this paper, we propose learning patch-channel correspondence to facilitate interpretable face forgery detection. Patch-channel correspondence aims to transform the latent features of a facial image into multi-channel interpretable features where each channel mainly encoders a corresponding facial patch. Towards this end, our approach embeds a feature reorganization layer into a deep neural network and simultaneously optimizes classification task and correspondence task via alternate optimization. The correspondence task accepts multiple zero-padding facial patch images and represents them into channel-aware interpretable representations. The task is solved by step-wisely learning channel-wise decorrelation and patch-channel alignment. Channel-wise decorrelation decouples latent features for class-specific discriminative channels to reduce feature complexity and channel correlation, while patch-channel alignment then models the pairwise correspondence between feature channels and facial patches. In this way, the learned model can automatically discover corresponding salient features associated to potential forgery regions during inference, providing discriminative localization of visualized evidences for face forgery detection while maintaining high detection accuracy. Extensive experiments on popular benchmarks clearly demonstrate the effectiveness of the proposed approach in interpreting face forgery detection without sacrificing accuracy. The source code is available at https://github.com/Jae35/IFFD
Keyword:
Forgery
Faces
Feature extraction
Deep learning
Decorrelation
Visualization
Task analysis
Face forgery detection
interpretable representation learning
patch-channel correspondence
期刊
IF:
13.7
论文数:
1.0W
被引数:
8.4W
机构
引用论文
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications解释深度神经网络及其以后: 方法和应用综述.png)
PROCEEDINGS OF THE IEEE
OAAI
PROCEEDINGS OF THE IEEEIF25.9
OAAI分享收藏Intercellular Adhesion Molecule 1 (ICAM-1) Gene Variant is Associated with Coronary Artery Calcification Independent of Soluble ICAM-1 Levels细胞间粘附分子1 (ICAM-1) 基因变异与冠状动脉钙化相关，与可溶性ICAM-1水平无关
PREAI
分享收藏
An Interpretable Deep Architecture for Similarity Learning Built Upon Hierarchical Concepts基于层次概念的相似性学习的可解释深度体系结构OAAI
OAAI分享收藏
查看更多内容