Extending Information Bottleneck Attribution to Video Sequences
This addresses the need for explainability in temporal models for video analysis, particularly for deepfake detection, but is incremental as it adapts an existing method to a new domain.
The authors tackled the problem of explainable video classification by adapting Information Bottlenecks for Attribution (IBA) to video sequences, resulting in VIBA, which generates temporally and spatially consistent explanations that align closely with human annotations for deepfake detection.
We introduce VIBA, a novel approach for explainable video classification by adapting Information Bottlenecks for Attribution (IBA) to video sequences. While most traditional explainability methods are designed for image models, our IBA framework addresses the need for explainability in temporal models used for video analysis. To demonstrate its effectiveness, we apply VIBA to video deepfake detection, testing it on two architectures: the Xception model for spatial features and a VGG11-based model for capturing motion dynamics through optical flow. Using a custom dataset that reflects recent deepfake generation techniques, we adapt IBA to create relevance and optical flow maps, visually highlighting manipulated regions and motion inconsistencies. Our results show that VIBA generates temporally and spatially consistent explanations, which align closely with human annotations, thus providing interpretability for video classification and particularly for deepfake detection.