Back to the Feature: Explaining Video Classifiers with Video Counterfactual Explanations

TL;DR

This paper introduces BTTF, a novel optimization framework for generating realistic, temporally coherent video counterfactual explanations that reveal the features influencing video classifier decisions.

Contribution

The paper presents a new method for creating physically plausible, smooth, and coherent video CFEs, addressing limitations of image-based approaches and ensuring explanations are faithful to the classifier.

Findings

BTTF generates realistic counterfactual videos across multiple datasets.

The method produces visually similar videos that effectively explain classifier decisions.

BTTF accelerates convergence with a progressive optimization strategy.

Abstract

Counterfactual explanations (CFEs) are minimal and semantically meaningful modifications of the input of a model that alter the model predictions. They highlight the decisive features the model relies on, providing contrastive interpretations for classifiers. State-of-the-art visual counterfactual explanation methods are designed to explain image classifiers. The generation of CFEs for video classifiers remains largely underexplored. For the counterfactual videos to be useful, they have to be physically plausible, temporally coherent, and exhibit smooth motion trajectories. Existing CFE image-based methods, designed to explain image classifiers, lack the capacity to generate temporally coherent, smooth and physically plausible video CFEs. To address this, we propose Back To The Feature (BTTF), an optimization framework that generates video CFEs. Our method introduces two novel features, 1) an optimization scheme to retrieve the initial latent noise conditioned by the first frame of the input video, 2) a two-stage optimization strategy to enable the search for counterfactual videos in the vicinity of the input video. Both optimization processes are guided solely by the target classifier, ensuring the explanation is faithful. To accelerate convergence, we also introduce a progressive optimization strategy that incrementally increases the number of denoising steps. Extensive experiments on video datasets such as Shape-Moving (motion classification), MEAD (emotion classification), and NTU RGB+D (action classification) show that our BTTF effectively generates valid, visually similar and realistic counterfactual videos that provide concrete insights into the classifier's decision-making mechanism.