【论文速递】CRANE: Post-Hoc Counterfactual Retrieval for Multimodal Classifiers

英文标题：CRANE: Post-Hoc Counterfactual Retrieval for Multimodal Classifiers

arXiv编号：2610.31594
作者：Franco Rugolon, Ioanna Miliou, Panagiotis Papapetrou
来源：arXiv
原文链接：https://arxiv.org/abs/2610.31594

中文摘要：
Counterfactual explanation methods have been introduced for unimodal settings, with dedicated frameworks for tabular, timeseries, text, and image data, yet no post-hoc method has been designed for classifiers that learn from multimodal inputs. Existing explainability methods for multimodal classifiers apply modality-specific attribution independently to each input, which fails to yield coherent explanations and does not transfer to arbitrary pre-trained multimodal architectures. To address these shortcomings, we present CRANE (Counterfactual Retrieval via Agnostic Nearest-neighbour Explanations), the first post-hoc, model-agnostic framework for nearest-neighbour multimodal counterfactual generation that retrieves real training examples from the target class as candidate explanations, ensuring plausibility by construction. Across four heterogeneous datasets and three fusion strategies, we show that Multimodal Consensus Retrieval (MC-R), which intersects per-modality neighbour sets to identify instances jointly close to the query in every modality, emerges as the strongest multimodal strategy, achieving the best or joint-best outcome on three of four datasets while grounding every explanation in the joint training distribution. Unimodal strategies remain competitive when a single modality dominates the decision boundary.

本文由华人空间 AI 论文助手自动抓取翻译，仅供学术交流。