paper-with-me

Papers

U-CECE: A Universal Multi-Resolution Framework for Conceptual Counterfactual Explanations

2026-04-09 · Angeliki Dimitriou, Nikolaos Chaidos, Maria Lymperaiou, Giorgos Filandrianos, Giorgos Stamou arxiv

As AI models grow more complex, explainability is essential for building trust, yet concept-based counterfactual methods still face a trade-off between expressivity and efficiency. Representing underlying concepts as atomic sets is fast but misses relational context, whereas full graph representations are more faithful but require solving the NP-hard Graph Edit Distance (GED) problem. We propose U-CECE, a unified, model-agnostic multi-resolution framework for conceptual counterfactual explanations that adapts to data regime and compute budget. U-CECE spans three levels of expressivity: atomic concepts for broad explanations, relational sets-of-sets for simple interactions, and structural graphs for full semantic structure. At the structural level, both a precision-oriented transductive mode based on supervised Graph Neural Networks (GNNs) and a scalable inductive mode based on unsupervised graph autoencoders (GAEs) are supported. Experiments on the structurally divergent CUB and Visual Genome datasets characterize the efficiency-expressivity trade-off across levels, while human surveys and LVLM-based evaluation show that the retrieved structural counterfactuals are semantically equivalent to, and often preferred over, exact GED-based ground-truth explanations.

📄 PDF Abstract BibTeX arXiv:2604.08295

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Learning to Look Closer: A New Instance-Wise Loss for Small Cerebral Lesion Segmentation

2025-11-21 · Luc Bouteille, Alexander Jaus, Jens Kleesiek, Rainer Stiefelhagen 외 arxiv

Traditional loss functions in medical image segmentation, such as Dice, often under-segment small lesions because their small relative volume contributes negligibly to the overall loss. To address this, instance-wise los…

Medical Image SegmentationLesion Segmentation

V-CECE: Visual Counterfactual Explanations via Conceptual Edits

2025-09-20 · Nikolaos Spanos, Maria Lymperaiou, Giorgos Filandrianos, Konstantinos Thomas 외 arxiv

Recent black-box counterfactual generation frameworks fail to take into account the semantic content of the proposed edits, while relying heavily on training to guide the generation process. We propose a novel, plug-and-…

Image Editing

Natural Language Inference Improves Compositionality in Vision-Language Models

2024-10-29 · Paola Cascante-Bonilla, Yu Hou, Yang Trista Cao, Hal Daumé III 외

Compositional reasoning in Vision-Language Models (VLMs) remains challenging as these models often struggle to relate objects, attributes, and spatial relationships. Recent methods aim to address these limitations by rel…

Natural Language Inference

Semantic Guided Large Scale Factor Remote Sensing Image Super-resolution with Generative Diffusion Prior

2024-05-11 · Ce Wang, Wanjie Sun

Remote sensing images captured by different platforms exhibit significant disparities in spatial resolution. Large scale factor super-resolution (SR) algorithms are vital for maximizing the utilization of low-resolution …

Image Super-ResolutionSuper-Resolution

Billions of Sketches Reveal Hidden Cultural Variation in Human Concepts

2026-07-08 · Arianna Pera, Mauro Martino, Nima Dehmamy, Douglas Guilbeault 외 arxiv

Claims about the universality of human concepts have been predominantly assessed through linguistic similarity across languages and cultures. However, words are effective as communication devices because they compress ri…