XRAI: Better Attributions Through Regions
Saliency methods can aid understanding of deep neural networks. Recent years have witnessed many improvements to saliency methods, as well as new ways for evaluating them. In this paper, we 1) present a novel region-based attribution method, XRAI, that builds upon integrated gradients (Sundararajan et al. 2017), 2) introduce evaluation methods for empirically assessing the quality of image-based saliency maps (Performance Information Curves (PICs)), and 3) contribute an axiom-based sanity check for attribution methods. Through empirical experiments and example results, we show that XRAI produces better results than other saliency methods for common models and the ImageNet dataset.
Code (2)
Similar Papers 제목 키워드 기반
xRAI: Explainable Representations through AI
We present xRAI an approach for extracting symbolic representations of the mathematical function a neural network was supposed to learn from the trained network. The approach is based on the idea of training a so-called …
Decision MakingDo We Need Responsible XR? Drawing on Responsible AI to Inform Ethical Research and Practice into XRAI / the Metaverse
This position paper for the CHI 2025 workshop "Everyday AR through AI-in-the-Loop" reflects on whether as a field HCI needs to define Responsible XR as a parallel to, and in conjunction with, Responsible AI, addressing t…
PositionGuided Integrated Gradients: An Adaptive Path Method for Removing Noise
Integrated Gradients (IG) is a commonly used feature attribution method for deep neural networks. While IG has many desirable properties, the method often produces spurious/noisy pixel attributions in regions that are no…
Knee-xRAI: An Explainable AI Framework for Automatic Kellgren-Lawrence Grading of Knee Osteoarthritis
Grading knee osteoarthritis (KOA) on plain radiographs is poorly reproducible across readers. A single-grade disagreement on the Kellgren-Lawrence (KL) scale can alter surgical management or redirect a patient from conse…
Provably Better Explanations with Optimized Aggregation of Feature Attributions
Using feature attributions for post-hoc explanations is a common practice to understand and verify the predictions of opaque machine learning models. Despite the numerous techniques available, individual methods often pr…