Assessment of the Reliablity of a Model's Decision by Generalizing Attribution to the Wavelet Domain
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}.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
One Wave to Explain Them All: A Unifying Perspective on Post-hoc Explainability
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 …
AllIlluminating Salient Contributions in Neuron Activation with Attribution Equilibrium
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 MakingNeSy-CSA: A Neuro-Symbolic Framework for Open-Ended Critical Scenario Attribution
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 GenerationToward Accountable AI-Generated Content on Social Platforms: Steganographic Attribution and Multimodal Harm Detection
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
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…