The 5th Explainable AI for Computer Vision (XAI4CV) Workshop
A Mechanistic Analysis of Training-Time Image Protection in Diffusion Models-
[pdf]
[bibtex]@InProceedings{Martin_2026_CVPR, author = {Martin, Michael and Chan, Garrick and Ma, Kwan-Liu}, title = {A Mechanistic Analysis of Training-Time Image Protection in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4068-4077} }
Can Cross-Layer Transcoders Replace Vision Transformer Activations? An Interpretable Perspective on Vision-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chatzoudis_2026_CVPR, author = {Chatzoudis, Gerasimos and Polyzos, Konstantinos D. and Li, Zhuowei and Gu, Difei and Moran, Gemma E. and Wang, Hao and Metaxas, Dimitris N.}, title = {Can Cross-Layer Transcoders Replace Vision Transformer Activations? An Interpretable Perspective on Vision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4016-4025} }
From Attribution to Action: A Human-Centered Application of Activation Steering-
[pdf]
[arXiv]
[bibtex]@InProceedings{Labarta_2026_CVPR, author = {Labarta, Tobias and Dreyer, Maximilian and Weitz, Katharina and Samek, Wojciech and Lapuschkin, Sebastian}, title = {From Attribution to Action: A Human-Centered Application of Activation Steering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4047-4057} }
Feature Attribution Stability Suite: How Stable Are Post-Hoc Attributions?-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Subramaniakuppusamy_2026_CVPR, author = {Subramaniakuppusamy, Kamalasankari and Gajjar, Jugal}, title = {Feature Attribution Stability Suite: How Stable Are Post-Hoc Attributions?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4078-4087} }
Investigating Anisotropy in Visual Grounding under Controlled Counterfactual Perturbations-
[pdf]
[arXiv]
[bibtex]@InProceedings{Lombardo_2026_CVPR, author = {Lombardo, Gabriele and Maiorana, Luigi and Presti, Liliana Lo and La Cascia, Marco}, title = {Investigating Anisotropy in Visual Grounding under Controlled Counterfactual Perturbations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4058-4067} }
DINO-QPM: Adapting Visual Foundation Models for Globally Interpretable Image Classification-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zimmermann_2026_CVPR, author = {Zimmermann, Robert and Norrenbrock, Thomas and Rosenhahn, Bodo}, title = {DINO-QPM: Adapting Visual Foundation Models for Globally Interpretable Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4121-4131} }
GLEaN: A Text-to-image Bias Detection Approach for Public Comprehension-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ding_2026_CVPR, author = {Ding, Bochu and Bent, Brinnae and Wendell, Augustus}, title = {GLEaN: A Text-to-image Bias Detection Approach for Public Comprehension}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4026-4036} }
Multi-Granularity Concept Whitening for Neural Network Interpretability-
[pdf]
[bibtex]@InProceedings{Barton_2026_CVPR, author = {Barton, Russell and Le, Viet Hung and Shan, Yunhong and Katopodis, Alexander and Donnelly, Jon and Chen, Eric and Chen, Chaofan and Rudin, Cynthia}, title = {Multi-Granularity Concept Whitening for Neural Network Interpretability}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3986-3995} }
Activation-Based Concept Extraction for Explainability in Image Classification-
[pdf]
[supp]
[bibtex]@InProceedings{Bianchi_2026_CVPR, author = {Bianchi, Matteo and Campi, Riccardo and De Santis, Antonio and Merengo, Sara and Brambilla, Marco}, title = {Activation-Based Concept Extraction for Explainability in Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3996-4005} }
How does My Model Fail? Automatic Identification and Interpretation of Physical Plausibility Failure Modes with Matryoshka Transcoders-
[pdf]
[arXiv]
[bibtex]@InProceedings{Tang_2026_CVPR, author = {Tang, Yiming and Sinha, Abhijeet and Liu, Dianbo}, title = {How does My Model Fail? Automatic Identification and Interpretation of Physical Plausibility Failure Modes with Matryoshka Transcoders}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4088-4100} }
Why Fake? Unveiling the Semantic Vocabulary of Deepfake Detectors-
[pdf]
[bibtex]@InProceedings{Vanian_2026_CVPR, author = {Vanian, Vazgken and Doumanoglou, Alexandros and Zarpalas, Dimitris}, title = {Why Fake? Unveiling the Semantic Vocabulary of Deepfake Detectors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4101-4110} }
FAME: Feature Activation Map Explanation on Image Classification and Face Recognition-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2026_CVPR, author = {Zhang, Xinyi and G\"unther, Manuel}, title = {FAME: Feature Activation Map Explanation on Image Classification and Face Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4111-4120} }
Faces in Focus: Evaluating Generalizability and Transferability of Facial Recognition Explainability Techniques for CNN-based Models-
[pdf]
[bibtex]@InProceedings{Borsukiewicz_2026_CVPR, author = {Borsukiewicz, Pawel and Diallo, El-hacen and Bonkoungou, Abdoul Aziz and Ouedraogo, Wendkuuni C and Klein, Jacques and Beumier, Charles and Bissyande, Tegawend\'e F.}, title = {Faces in Focus: Evaluating Generalizability and Transferability of Facial Recognition Explainability Techniques for CNN-based Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4006-4015} }
A Benchmark Study on the Reliability of Explainability Methods-
[pdf]
[supp]
[bibtex]@InProceedings{Kowsar_2026_CVPR, author = {Kowsar, Ibna and Rezaei, Shahbaz and Meng, Fanyu and Liu, Xin}, title = {A Benchmark Study on the Reliability of Explainability Methods}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4037-4046} }

