Communities
Connect sessions
AI calendar
Organizations
Join Slack
Contact Sales
Search
Open menu
Home
Papers
2202.03482
Cited By
v1
v2
v3 (latest)
Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence
International Conference on Learning Representations (ICLR), 2022
7 February 2022
Frederik Pahde
Maximilian Dreyer
Leander Weber
Moritz Weckbecker
Christopher J. Anders
Thomas Wiegand
Wojciech Samek
Sebastian Lapuschkin
Re-assign community
ArXiv (abs)
PDF
HTML
Papers citing
"Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence"
49 / 49 papers shown
Probing the Probes: Methods and Metrics for Concept Alignment
Jacob Lysnæs-Larsen
Marte Eggen
Inga Strümke
LLMSV
240
0
0
06 Nov 2025
Mitigating Clever Hans Strategies in Image Classifiers through Generating Counterexamples
Sidney Bender
Ole Delzer
J. Herrmann
Heike Marxfeld
Klaus-Robert Müller
G. Montavon
274
3
0
20 Oct 2025
TDHook: A Lightweight Framework for Interpretability
Yoann Poupart
AI4CE
190
0
0
29 Sep 2025
Concept activation vectors: a unifying view and adversarial attacks
Ekkehard Schnoor
Malik Tiomoko
Jawher Said
Alex Jung
Wojciech Samek
AAML
138
0
0
26 Sep 2025
In-hoc Concept Representations to Regularise Deep Learning in Medical Imaging
V. Corbetta
Floris Six Dijkstra
R. Beets-Tan
Hoel Kervadec
Kristoffer Wickstrøm
Wilson Silva
OOD
163
0
0
19 Aug 2025
From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance
Maximilian Dreyer
Lorenz Hufe
J. Berend
Thomas Wiegand
Sebastian Lapuschkin
Wojciech Samek
279
2
0
26 May 2025
FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks
Laines Schmalwasser
Niklas Penzel
Joachim Denzler
Julia Niebling
223
5
0
23 May 2025
Steering CLIP's vision transformer with sparse autoencoders
Sonia Joseph
Praneet Suresh
Ethan Goldfarb
Lorenz Hufe
Yossi Gandelsman
Robert Graham
Danilo Bzdok
Wojciech Samek
Blake A. Richards
347
16
0
11 Apr 2025
Post-Hoc Concept Disentanglement: From Correlated to Isolated Concept Representations
Eren Erogullari
Sebastian Lapuschkin
Wojciech Samek
Frederik Pahde
LLMSV
CoGe
412
1
0
07 Mar 2025
Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?
Jae Hee Lee
Georgii Mikriukov
Gesina Schwalbe
Stefan Wermter
D. Wolter
370
13
0
20 Sep 2024
Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression
Dilyara Bareeva
Maximilian Dreyer
Frederik Pahde
Wojciech Samek
Sebastian Lapuschkin
KELM
268
6
0
15 Apr 2024
Manipulating Feature Visualizations with Gradient Slingshots
Dilyara Bareeva
Marina M.-C. Höhne
Alexander Warnecke
Lukas Pirch
Klaus-Robert Müller
Konrad Rieck
Sebastian Lapuschkin
Kirill Bykov
AAML
479
7
0
11 Jan 2024
Emergent Linear Representations in World Models of Self-Supervised Sequence Models
BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP), 2023
Neel Nanda
Andrew Lee
Martin Wattenberg
FAtt
MILM
374
295
0
02 Sep 2023
From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space
AAAI Conference on Artificial Intelligence (AAAI), 2023
Maximilian Dreyer
Frederik Pahde
Christopher J. Anders
Wojciech Samek
Sebastian Lapuschkin
AI4CE
301
19
0
18 Aug 2023
FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods
IEEE International Conference on Computer Vision (ICCV), 2023
Robin Hesse
Simone Schaub-Meyer
Stefan Roth
AAML
310
50
0
11 Aug 2023
Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models
International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2023
Frederik Pahde
Maximilian Dreyer
Wojciech Samek
Sebastian Lapuschkin
217
25
0
22 Mar 2023
Concept Algebra for (Score-Based) Text-Controlled Generative Models
Neural Information Processing Systems (NeurIPS), 2023
Zihao Wang
Lin Gui
Jeffrey Negrea
Victor Veitch
CoGe
DiffM
695
66
0
07 Feb 2023
Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees
Johanna Vielhaben
Stefan Blücher
Nils Strodthoff
267
49
0
27 Jan 2023
CRAFT: Concept Recursive Activation FacTorization for Explainability
Computer Vision and Pattern Recognition (CVPR), 2022
Thomas Fel
Agustin Picard
Louis Bethune
Thibaut Boissin
David Vigouroux
Julien Colin
Rémi Cadène
Thomas Serre
409
187
0
17 Nov 2022
Concept Activation Regions: A Generalized Framework For Concept-Based Explanations
Neural Information Processing Systems (NeurIPS), 2022
Jonathan Crabbé
M. Schaar
373
74
0
22 Sep 2022
Toy Models of Superposition
Nelson Elhage
Tristan Hume
Catherine Olsson
Nicholas Schiefer
T. Henighan
...
Sam McCandlish
Jared Kaplan
Dario Amodei
Martin Wattenberg
C. Olah
AAML
MILM
1.8K
682
0
21 Sep 2022
From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation
Nature Machine Intelligence (Nat. Mach. Intell.), 2022
Reduan Achtibat
Maximilian Dreyer
Ilona Eisenbraun
S. Bosse
Thomas Wiegand
Wojciech Samek
Sebastian Lapuschkin
FAtt
316
212
0
07 Jun 2022
Post-hoc Concept Bottleneck Models
International Conference on Learning Representations (ICLR), 2022
Mert Yuksekgonul
Maggie Wang
James Zou
507
280
0
31 May 2022
Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement
Information Fusion (Inf. Fusion), 2022
Leander Weber
Sebastian Lapuschkin
Alexander Binder
Wojciech Samek
293
131
0
15 Mar 2022
Diffusion Autoencoders: Toward a Meaningful and Decodable Representation
Konpat Preechakul
Nattanat Chatthee
Suttisak Wizadwongsa
Supasorn Suwajanakorn
SyDa
DiffM
537
567
0
30 Nov 2021
Acquisition of Chess Knowledge in AlphaZero
Thomas McGrath
A. Kapishnikov
Nenad Tomašev
Adam Pearce
Demis Hassabis
Been Kim
Ulrich Paquet
Vladimir Kramnik
521
196
0
17 Nov 2021
ResNet strikes back: An improved training procedure in timm
Ross Wightman
Hugo Touvron
Edouard Grave
AI4TS
689
596
0
01 Oct 2021
Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy
Christopher J. Anders
David Neumann
Wojciech Samek
K. Müller
Sebastian Lapuschkin
272
81
0
24 Jun 2021
ImageNet-21K Pretraining for the Masses
T. Ridnik
Emanuel Ben-Baruch
Asaf Noy
Lihi Zelnik-Manor
SSeg
VLM
CLIP
978
901
0
22 Apr 2021
Robust Semantic Interpretability: Revisiting Concept Activation Vectors
J. Pfau
A. Young
Jerome Wei
Maria L. Wei
Michael J. Keiser
FAtt
162
16
0
06 Apr 2021
EfficientNetV2: Smaller Models and Faster Training
International Conference on Machine Learning (ICML), 2021
Mingxing Tan
Quoc V. Le
EgoV
1.7K
4,083
0
01 Apr 2021
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Alexey Dosovitskiy
Lucas Beyer
Alexander Kolesnikov
Dirk Weissenborn
Xiaohua Zhai
...
Matthias Minderer
G. Heigold
Sylvain Gelly
Jakob Uszkoreit
N. Houlsby
ViT
1.6K
60,084
0
22 Oct 2020
Understanding the Role of Individual Units in a Deep Neural Network
Proceedings of the National Academy of Sciences of the United States of America (PNAS), 2020
David Bau
Jun-Yan Zhu
Hendrik Strobelt
Àgata Lapedriza
Bolei Zhou
Antonio Torralba
GAN
426
513
0
10 Sep 2020
Rethinking Channel Dimensions for Efficient Model Design
Dongyoon Han
Sangdoo Yun
Byeongho Heo
Y. Yoo
3DV
322
108
0
02 Jul 2020
Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectors
Ruihan Zhang
Prashan Madumal
Tim Miller
Krista A. Ehinger
Benjamin I. P. Rubinstein
FAtt
468
140
0
27 Jun 2020
Concept Whitening for Interpretable Image Recognition
Nature Machine Intelligence (NMI), 2020
Zhi Chen
Yijie Bei
Cynthia Rudin
FAtt
703
363
0
05 Feb 2020
Towards Best Practice in Explaining Neural Network Decisions with LRP
IEEE International Joint Conference on Neural Network (IJCNN), 2019
M. Kohlbrenner
Alexander Bauer
Shinichi Nakajima
Alexander Binder
Wojciech Samek
Sebastian Lapuschkin
473
170
0
22 Oct 2019
BCN20000: Dermoscopic Lesions in the Wild
Scientific Data (Sci Data), 2019
Marc Combalia
Noel Codella
V. Rotemberg
Brian Helba
Verónica Vilaplana
...
Cristina Carrera
Alicia Barreiro
Allan Halpern
S. Puig
J. Malvehy
422
605
0
06 Aug 2019
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
International Conference on Machine Learning (ICML), 2019
Mingxing Tan
Quoc V. Le
3DV
MedIm
880
23,117
0
28 May 2019
Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
Been Kim
Martin Wattenberg
Justin Gilmer
Carrie J. Cai
James Wexler
F. Viégas
Rory Sayres
FAtt
720
2,229
0
30 Nov 2017
Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)
Noel Codella
D. Gutman
M. E. Celebi
Brian Helba
Michael Marchetti
...
Aadi Kalloo
Konstantinos Liopyris
N. Mishra
Harald Kittler
Allan Halpern
805
2,551
0
13 Oct 2017
A Unified Approach to Interpreting Model Predictions
Scott M. Lundberg
Su-In Lee
FAtt
5.2K
32,516
0
22 May 2017
Learning how to explain neural networks: PatternNet and PatternAttribution
Pieter-Jan Kindermans
Kristof T. Schütt
Maximilian Alber
K. Müller
D. Erhan
Been Kim
Sven Dähne
XAI
FAtt
336
368
0
16 May 2017
Learning to Generate Reviews and Discovering Sentiment
Alec Radford
Rafal Jozefowicz
Ilya Sutskever
408
541
0
05 Apr 2017
Aggregated Residual Transformations for Deep Neural Networks
Saining Xie
Ross B. Girshick
Piotr Dollár
Zhuowen Tu
Kaiming He
1.3K
11,487
0
16 Nov 2016
Understanding intermediate layers using linear classifier probes
International Conference on Learning Representations (ICLR), 2016
Guillaume Alain
Yoshua Bengio
FAtt
847
1,300
0
05 Oct 2016
Deep Residual Learning for Image Recognition
Kaiming He
Xinming Zhang
Shaoqing Ren
Jian Sun
MedIm
4.2K
224,064
0
10 Dec 2015
Deep Learning Face Attributes in the Wild
IEEE International Conference on Computer Vision (ICCV), 2014
Ziwei Liu
Ping Luo
Xiaogang Wang
Xiaoou Tang
CVBM
1.6K
9,434
0
28 Nov 2014
Very Deep Convolutional Networks for Large-Scale Image Recognition
International Conference on Learning Representations (ICLR), 2014
Karen Simonyan
Andrew Zisserman
FAtt
MDE
4.0K
110,317
0
04 Sep 2014
1
Page 1 of 1
