paper-with-me

Papers

Assessment of the Reliablity of a Model's Decision by Generalizing Attribution to the Wavelet Domain

2023-05-24 · Gabriel Kasmi, Laurent Dubus, Yves-Marie Saint Drenan, Philippe Blanc

Neural networks have shown remarkable performance in computer vision, but their deployment in numerous scientific and technical fields is challenging due to their black-box nature. Scientists and practitioners need to evaluate the reliability of a decision, i.e., to know simultaneously if a model relies on the relevant features and whether these features are robust to image corruptions. Existing attribution methods aim to provide human-understandable explanations by highlighting important regions in the image domain, but fail to fully characterize a decision process's reliability. To bridge this gap, we introduce the Wavelet sCale Attribution Method (WCAM), a generalization of attribution from the pixel domain to the space-scale domain using wavelet transforms. Attribution in the wavelet domain reveals where and on what scales the model focuses, thus enabling us to assess whether a decision is reliable. Our code is accessible here: \url{https://github.com/gabrielkasmi/spectral-attribution}.

📄 PDF Abstract BibTeX arXiv:2305.14979

Code (1)

gabrielkasmi/spectral-attribution 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

fail 설명 없음

Similar Papers 제목 키워드 기반

One Wave to Explain Them All: A Unifying Perspective on Post-hoc Explainability

2024-10-02 · Gabriel Kasmi, Amandine Brunetto, Thomas Fel, Jayneel Parekh

Despite the growing use of deep neural networks in safety-critical decision-making, their inherent black-box nature hinders transparency and interpretability. Explainable AI (XAI) methods have thus emerged to understand …

All

Illuminating Salient Contributions in Neuron Activation with Attribution Equilibrium

2022-05-23 · Woo-Jeoung Nam, Seong-Whan Lee

With the remarkable success of deep neural networks, there is a growing interest in research aimed at providing clear interpretations of their decision-making processes. In this paper, we introduce Attribution Equilibriu…

Decision Making

NeSy-CSA: A Neuro-Symbolic Framework for Open-Ended Critical Scenario Attribution

2026-07-04 · Qitong Chu, Xunjie He, Chen Deng, Huaxin Pei 외 arxiv

Understanding why discovered scenarios become critical in scenario-based testing is essential for effectively leveraging them in decision-making systems. Reasoning about such criticality can be formulated as an attributi…

Explanation Generation

Toward Accountable AI-Generated Content on Social Platforms: Steganographic Attribution and Multimodal Harm Detection

2026-04-12 · Xinlei Guan, David Arosemena, Tejaswi Dhandu, Kuan Huang 외 arxiv

The rapid growth of generative AI has introduced new challenges in content moderation and digital forensics. In particular, benign AI-generated images can be paired with harmful or misleading text, creating difficult-to-…

Diagnosing the Reliability of LLM-as-a-Judge via Item Response Theory

2026-01-31 · Junhyuk Choi, Sohhyung Park, Chanhee Cho, Hyeonchu Park 외 arxiv

While LLM-as-a-Judge is widely used in automated evaluation, existing validation practices primarily operate at the level of observed outputs, offering limited insight into whether LLM judges themselves function as stabl…