New Definitions and Evaluations for Saliency Methods: Staying Intrinsic,
Complete and Sound

New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound

5 November 2022

Dingli Yu

ArXiv (abs)PDF HTML

Papers citing "New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound"

7 / 7 papers shown

Title
Concept-Centric Token Interpretation for Vector-Quantized Generative Models Tianze Yang Yucheng Shi Mengnan Du Xuansheng Wu Qiaoyu Tan Jin Sun Ninghao Liu 45 0 0 31 May 2025
Noise-Free Explanation for Driving Action Prediction Hongbo Zhu Theodor Wulff R. S. Maharjan Jinpei Han Angelo Cangelosi AAML FAtt 75 0 0 08 Jul 2024
Evaluating Saliency Explanations in NLP by Crowdsourcing Xiaotian Lu Jiyi Li Zhen Wan Xiaofeng Lin Koh Takeuchi Hisashi Kashima XAI FAtt LRM 70 1 0 17 May 2024
LIPEx-Locally Interpretable Probabilistic Explanations-To Look Beyond The True Class Hongbo Zhu Angelo Cangelosi Procheta Sen Anirbit Mukherjee FAtt 77 0 0 07 Oct 2023
Distance-Aware eXplanation Based Learning Misgina Tsighe Hagos Niamh Belton Kathleen M. Curran Brian Mac Namee FAtt 64 0 0 11 Sep 2023
Harmonizing Feature Attributions Across Deep Learning Architectures: Enhancing Interpretability and Consistency Md Abdul Kadir G. Addluri Daniel Sonntag FAtt 66 1 0 05 Jul 2023
Understanding and Improving Feature Learning for Out-of-Distribution Generalization Yongqiang Chen Wei Huang Kaiwen Zhou Yatao Bian Bo Han James Cheng MLT OOD OODD 85 29 0 22 Apr 2023