Improving Feature Attribution through Input-specific Network Pruning

v1v2 (latest)

Improving Feature Attribution through Input-specific Network Pruning

25 November 2019

Soroosh Baselizadeh

Saurabh Khanduja

Christian Rupprecht

Nassir Navab

ArXiv (abs)PDF HTML

Papers citing "Improving Feature Attribution through Input-specific Network Pruning"

9 / 9 papers shown

Title
Smaller is Better: Enhancing Transparency in Vehicle AI Systems via Pruning Sanish Suwal Shaurya Garg Dipkamal Bhusal Michael Clifford Nidhi Rastogi AAML 86 1 0 24 Sep 2025
SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation Dennis Fucci Marco Gaido Beatrice Savoldi Matteo Negri Mauro Cettolo L. Bentivogli 499 5 0 03 Nov 2024
sMRI-PatchNet: A novel explainable patch-based deep learning network for Alzheimer's disease diagnosis and discriminative atrophy localisation with Structural MRIIEEE Access (IEEE Access), 2023 Xin Zhang Liangxiu Han Lianghao Han Haoming Chen Darren Dancey Daoqiang Zhang MedIm 191 16 0 17 Feb 2023
Less is More: The Influence of Pruning on the Explainability of CNNs David Weber F. Merkle Pascal Schöttle Stephan Schlögl Martin Nocker FAtt 461 5 0 17 Feb 2023
Explainable Model-Agnostic Similarity and Confidence in Face Verification Martin Knoche Torben Teepe S. Hörmann Gerhard Rigoll AAML CVBM 165 20 0 24 Nov 2022
New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and SoundNeural Information Processing Systems (NeurIPS), 2022 Arushi Gupta Nikunj Saunshi Dingli Yu Kaifeng Lyu Sanjeev Arora AAML FAtt XAI 120 8 0 05 Nov 2022
Analyzing the Effects of Handling Data Imbalance on Learned Features from Medical Images by Looking Into the Models Ashkan Khakzar Yawei Li Yang Zhang Mirac Sanisoglu Seong Tae Kim Mina Rezaei B. Bischl Nassir Navab 153 0 0 04 Apr 2022
Adversarial Infidelity Learning for Model Interpretation Jian Liang Bing Bai Yuren Cao Kun Bai Haiwei Yang AAML 167 19 0 09 Jun 2020
Restricting the Flow: Information Bottlenecks for AttributionInternational Conference on Learning Representations (ICLR), 2020 Karl Schulz Leon Sixt Federico Tombari Tim Landgraf FAtt 460 206 0 02 Jan 2020