Understanding Deep Networks via Extremal Perturbations and Smooth Masks

18 October 2019

Andrea Vedaldi

Papers citing "Understanding Deep Networks via Extremal Perturbations and Smooth Masks"

50 / 75 papers shown

Title
Attention IoU: Examining Biases in CelebA using Attention Maps Aaron Serianni Tyler Zhu Olga Russakovsky V. V. Ramaswamy 39 0 0 25 Mar 2025
Model Lakes Koyena Pal David Bau Renée J. Miller 63 0 0 24 Feb 2025
Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment Harrish Thasarathan Julian Forsyth Thomas Fel M. Kowal Konstantinos G. Derpanis 105 7 0 06 Feb 2025
Generating visual explanations from deep networks using implicit neural representations Michal Byra Henrik Skibbe GAN FAtt 29 0 0 20 Jan 2025
Layerwise Change of Knowledge in Neural Networks Xu Cheng Lei Cheng Zhaoran Peng Yang Xu Tian Han Quanshi Zhang KELM FAtt 33 6 0 13 Sep 2024
Human-inspired Explanations for Vision Transformers and Convolutional Neural Networks Mahadev Prasad Panda Matteo Tiezzi Martina Vilas Gemma Roig Bjoern M. Eskofier Dario Zanca ViT AAML 29 1 0 04 Aug 2024
Interpreting Low-level Vision Models with Causal Effect Maps Jinfan Hu Jinjin Gu Shiyao Yu Fanghua Yu Zheyuan Li Zhiyuan You Chaochao Lu Chao Dong CML 48 2 0 29 Jul 2024
Graphical Perception of Saliency-based Model Explanations Yayan Zhao Mingwei Li Matthew Berger XAI FAtt 36 2 0 11 Jun 2024
Made to Order: Discovering monotonic temporal changes via self-supervised video ordering Charig Yang Weidi Xie Andrew Zisserman 34 1 0 25 Apr 2024
What Sketch Explainability Really Means for Downstream Tasks Hmrishav Bandyopadhyay Pinaki Nath Chowdhury A. Bhunia Aneeshan Sain Tao Xiang Yi-Zhe Song 30 4 0 14 Mar 2024
Explainable Multi-Camera 3D Object Detection with Transformer-Based Saliency Maps Till Beemelmanns Wassim Zahr Lutz Eckstein 27 0 0 22 Dec 2023
Occlusion Sensitivity Analysis with Augmentation Subspace Perturbation in Deep Feature Space Pedro Valois Koichiro Niinuma Kazuhiro Fukui AAML 24 4 0 25 Nov 2023
Zero-shot Translation of Attention Patterns in VQA Models to Natural Language Leonard Salewski A. Sophia Koepke Hendrik P. A. Lensch Zeynep Akata 29 2 0 08 Nov 2023
Multiple Different Black Box Explanations for Image Classifiers Hana Chockler D. A. Kelly Daniel Kroening FAtt 19 0 0 25 Sep 2023
Interpretability-Aware Vision Transformer Yao Qiang Chengyin Li Prashant Khanduri D. Zhu ViT 80 7 0 14 Sep 2023
Generative Perturbation Analysis for Probabilistic Black-Box Anomaly Attribution T. Idé Naoki Abe 33 4 0 09 Aug 2023
Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability Usha Bhalla Suraj Srinivas Himabindu Lakkaraju FAtt CML 23 6 0 27 Jul 2023
DeepMediX: A Deep Learning-Driven Resource-Efficient Medical Diagnosis Across the Spectrum Kishore Babu Nampalle Pradeep Singh Vivek Narayan Uppala Balasubramanian Raman MedIm 19 2 0 01 Jul 2023
Decom--CAM: Tell Me What You See, In Details! Feature-Level Interpretation via Decomposition Class Activation Map Yuguang Yang Runtang Guo Shen-Te Wu Yimi Wang Juan Zhang Xuan Gong Baochang Zhang 17 0 0 27 May 2023
UFO: A unified method for controlling Understandability and Faithfulness Objectives in concept-based explanations for CNNs V. V. Ramaswamy Sunnie S. Y. Kim Ruth C. Fong Olga Russakovsky 27 0 0 27 Mar 2023
ICICLE: Interpretable Class Incremental Continual Learning Dawid Rymarczyk Joost van de Weijer Bartosz Zieliñski Bartlomiej Twardowski CLL 24 28 0 14 Mar 2023
A Lifted Bregman Formulation for the Inversion of Deep Neural Networks Xiaoyu Wang Martin Benning 28 2 0 01 Mar 2023
ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts Mikolaj Sacha Dawid Rymarczyk Lukasz Struski Jacek Tabor Bartosz Zieliñski VLM 30 29 0 28 Jan 2023
Opti-CAM: Optimizing saliency maps for interpretability Hanwei Zhang Felipe Torres R. Sicre Yannis Avrithis Stéphane Ayache 28 22 0 17 Jan 2023
Attribution-based XAI Methods in Computer Vision: A Review Kumar Abhishek Deeksha Kamath 27 18 0 27 Nov 2022
Explaining Image Classifiers with Multiscale Directional Image Representation Stefan Kolek Robert Windesheim Héctor Andrade-Loarca Gitta Kutyniok Ron Levie 23 4 0 22 Nov 2022
ViT-CX: Causal Explanation of Vision Transformers Weiyan Xie Xiao-hui Li Caleb Chen Cao Nevin L.Zhang ViT 21 17 0 06 Nov 2022
PlanT: Explainable Planning Transformers via Object-Level Representations Katrin Renz Kashyap Chitta Otniel-Bogdan Mercea A. Sophia Koepke Zeynep Akata Andreas Geiger ViT 33 94 0 25 Oct 2022
Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition Tomoya Nitta Tsubasa Hirakawa H. Fujiyoshi Toru Tamaki 52 0 0 27 Jul 2022
Adaptive occlusion sensitivity analysis for visually explaining video recognition networks Tomoki Uchiyama Naoya Sogi S. Iizuka Koichiro Niinuma Kazuhiro Fukui 13 2 0 26 Jul 2022
Explanation-based Counterfactual Retraining(XCR): A Calibration Method for Black-box Models Liu Zhendong Wenyu Jiang Yan Zhang Chongjun Wang CML 6 0 0 22 Jun 2022
Spatial-temporal Concept based Explanation of 3D ConvNets Yi Ji Yu Wang K. Mori Jien Kato 3DPC FAtt 16 7 0 09 Jun 2022
Dual Decomposition of Convex Optimization Layers for Consistent Attention in Medical Images Tom Ron M. Weiler-Sagie Tamir Hazan FAtt MedIm 19 6 0 06 Jun 2022
On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition Yue Song N. Sebe Wei Wang 18 33 0 26 May 2022
What You See is What You Classify: Black Box Attributions Steven Stalder Nathanael Perraudin R. Achanta F. Pérez-Cruz Michele Volpi FAtt 24 9 0 23 May 2022
Learnable Visual Words for Interpretable Image Recognition Wenxi Xiao Zhengming Ding Hongfu Liu VLM 8 2 0 22 May 2022
It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers Zheng Tang Mihai Surdeanu 16 6 0 25 Apr 2022
CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations Leonard Salewski A. Sophia Koepke Hendrik P. A. Lensch Zeynep Akata LRM NAI 25 20 0 05 Apr 2022
Human-Centered Concept Explanations for Neural Networks Chih-Kuan Yeh Been Kim Pradeep Ravikumar FAtt 25 25 0 25 Feb 2022
Deeply Explain CNN via Hierarchical Decomposition Mingg-Ming Cheng Peng-Tao Jiang Linghao Han Liang Wang Philip H. S. Torr FAtt 48 15 0 23 Jan 2022
HIVE: Evaluating the Human Interpretability of Visual Explanations Sunnie S. Y. Kim Nicole Meister V. V. Ramaswamy Ruth C. Fong Olga Russakovsky 58 114 0 06 Dec 2021
Self-Interpretable Model with TransformationEquivariant Interpretation Yipei Wang Xiaoqian Wang 24 23 0 09 Nov 2021
Gradient Frequency Modulation for Visually Explaining Video Understanding Models Xinmiao Lin Wentao Bao Matthew Wright Yu Kong FAtt AAML 22 2 0 01 Nov 2021
Explaining Latent Representations with a Corpus of Examples Jonathan Crabbé Zhaozhi Qian F. Imrie M. Schaar FAtt 16 37 0 28 Oct 2021
Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models? Thang M. Pham Trung H. Bui Long Mai Anh Totti Nguyen 21 7 0 22 Oct 2021
TorchEsegeta: Framework for Interpretability and Explainability of Image-based Deep Learning Models S. Chatterjee Arnab Das Chirag Mandal Budhaditya Mukhopadhyay Manish Vipinraj Aniruddh Shukla R. Rao Chompunuch Sarasaen Oliver Speck A. Nürnberger MedIm 21 14 0 16 Oct 2021
Consistent Explanations by Contrastive Learning Vipin Pillai Soroush Abbasi Koohpayegani Ashley Ouligian Dennis Fong Hamed Pirsiavash FAtt 18 21 0 01 Oct 2021
DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applications Dongqi Han Zhiliang Wang Wenqi Chen Ying Zhong Su Wang Han Zhang Jiahai Yang Xingang Shi Xia Yin AAML 16 76 0 23 Sep 2021
PACE: Posthoc Architecture-Agnostic Concept Extractor for Explaining CNNs V. Kamakshi Uday Gupta N. C. Krishnan 8 18 0 31 Aug 2021
Understanding of Kernels in CNN Models by Suppressing Irrelevant Visual Features in Images Jiafan Zhuang Wanying Tao Jianfei Xing Wei Shi Ruixuan Wang Weishi Zheng FAtt 32 3 0 25 Aug 2021