Systematic Trust in AI Models: Ensuring Fairness, Reliability, Explainability, and Accountability in Machine Learning Frameworks


From Global to Local: Social Bias Transfer in CLIP
Ryan Ramos,
Yusuke Hirota,
Yuta Nakashima,
Noa Garcia
[pdf] [arXiv]
[bibtex]
@InProceedings{Ramos_2025_ICCV, author = {Ramos, Ryan and Hirota, Yusuke and Nakashima, Yuta and Garcia, Noa}, title = {From Global to Local: Social Bias Transfer in CLIP}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {241-250} }

Extracting Uncertainty Estimates from Mixtures of Experts for Semantic Segmentation
Svetlana Pavlitska,
Beyza Keskin,
Alwin Faßbender,
Christian Hubschneider,
J. Marius Zöllner
[pdf]
[bibtex]
@InProceedings{Pavlitska_2025_ICCV, author = {Pavlitska, Svetlana and Keskin, Beyza and Fa{\ss}bender, Alwin and Hubschneider, Christian and Z\"ollner, J. Marius}, title = {Extracting Uncertainty Estimates from Mixtures of Experts for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {311-320} }

Explain with Confidence: Fusing Saliency Maps for Faithful and Interpretable Weakly-Supervised Model
Ayush Somani,
Arif Ahmed Sekh,
Dilip K. Prasad
[pdf]
[bibtex]
@InProceedings{Somani_2025_ICCV, author = {Somani, Ayush and Sekh, Arif Ahmed and Prasad, Dilip K.}, title = {Explain with Confidence: Fusing Saliency Maps for Faithful and Interpretable Weakly-Supervised Model}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {290-299} }

COOkeD: Ensemble-Based OOD Detection in the Era of Zero-Shot CLIP
Galadrielle Humblot-Renaux,
Gianni Franchi,
Sergio Escalera,
Thomas B. Moeslund
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Humblot-Renaux_2025_ICCV, author = {Humblot-Renaux, Galadrielle and Franchi, Gianni and Escalera, Sergio and Moeslund, Thomas B.}, title = {COOkeD: Ensemble-Based OOD Detection in the Era of Zero-Shot CLIP}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {261-271} }

Is It Certainly a Deepfake? Reliability Analysis in Detection & Generation Ecosystem
Neslihan Kose,
Anthony Rhodes,
Umur Aybars Ciftci,
Ilke Demir
[pdf] [arXiv]
[bibtex]
@InProceedings{Kose_2025_ICCV, author = {Kose, Neslihan and Rhodes, Anthony and Ciftci, Umur Aybars and Demir, Ilke}, title = {Is It Certainly a Deepfake? Reliability Analysis in Detection \& Generation Ecosystem}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {279-289} }

Data Bias Mitigation and Evaluation Framework for Diffusion-based Generative Face Models
Hao Yu,
Margrit Betke,
Sarah Adel Bargal
[pdf]
[bibtex]
@InProceedings{Yu_2025_ICCV, author = {Yu, Hao and Betke, Margrit and Bargal, Sarah Adel}, title = {Data Bias Mitigation and Evaluation Framework for Diffusion-based Generative Face Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {300-310} }

Enhancing Vision-Language Models for Zero-Shot Video Action Recognition via Visual-Textual Refinement and Improved Interpretability
Adeel Yousaf,
Mubarak Shah
[pdf]
[bibtex]
@InProceedings{Yousaf_2025_ICCV, author = {Yousaf, Adeel and Shah, Mubarak}, title = {Enhancing Vision-Language Models for Zero-Shot Video Action Recognition via Visual-Textual Refinement and Improved Interpretability}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {331-340} }

Robust Experts: The Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers
Svetlana Pavlitska,
Haixi Fan,
Konstantin Ditschuneit,
J. Marius Zöllner
[pdf] [arXiv]
[bibtex]
@InProceedings{Pavlitska_2025_ICCV, author = {Pavlitska, Svetlana and Fan, Haixi and Ditschuneit, Konstantin and Z\"ollner, J. Marius}, title = {Robust Experts: The Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {251-260} }

GenAI Confessions: Black-box Membership Inference for Generative Image Models
Matyas Bohacek,
Hany Farid
[pdf] [arXiv]
[bibtex]
@InProceedings{Bohacek_2025_ICCV, author = {Bohacek, Matyas and Farid, Hany}, title = {GenAI Confessions: Black-box Membership Inference for Generative Image Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {321-330} }

Are X-ray Landmark Detection Models Fair? A Preliminary Assessment and Mitigation Strategy
Roberto Di Via,
Massimiliano Ciranni,
Davide Marinelli,
Allison Clement,
Nikil Patel,
Julian Wyatt,
Francesca Odone,
Matteo Santacesaria,
Irina Voiculescu,
Vito Paolo Pastore
[pdf]
[bibtex]
@InProceedings{Di_Via_2025_ICCV, author = {Di Via, Roberto and Ciranni, Massimiliano and Marinelli, Davide and Clement, Allison and Patel, Nikil and Wyatt, Julian and Odone, Francesca and Santacesaria, Matteo and Voiculescu, Irina and Pastore, Vito Paolo}, title = {Are X-ray Landmark Detection Models Fair? A Preliminary Assessment and Mitigation Strategy}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {272-278} }

ImageNet-BG: A Toolkit and Dataset for Evaluating Vision Model Robustness Against Background Variations
Łukasz Piekarek,
Kamil Szyc
[pdf] [supp]
[bibtex]
@InProceedings{Piekarek_2025_ICCV, author = {Piekarek, {\L}ukasz and Szyc, Kamil}, title = {ImageNet-BG: A Toolkit and Dataset for Evaluating Vision Model Robustness Against Background Variations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {231-240} }