CVPR 2025 Open Access Repository

Uncertainty Quantification for Computer Vision

Uncertainty Quantification for Gradient-based Explanations in Neural Networks: Mihir Mulye,

Matias Valdenegro-Toro; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mulye_2025_CVPR, author = {Mulye, Mihir and Valdenegro-Toro, Matias}, title = {Uncertainty Quantification for Gradient-based Explanations in Neural Networks}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {1752-1760} }
D-Feat Occlusions: Diffusion Features for Robustness to Partial Visual Occlusions in Object Recognition: Rupayan Mallick,

Sibo Dong,

Nataniel Ruiz,

Sarah Adel Bargal; [pdf]
[bibtex]
@InProceedings{Mallick_2025_CVPR, author = {Mallick, Rupayan and Dong, Sibo and Ruiz, Nataniel and Bargal, Sarah Adel}, title = {D-Feat Occlusions: Diffusion Features for Robustness to Partial Visual Occlusions in Object Recognition}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {1722-1731} }
WQLCP: Weighted Adaptive Conformal Prediction for Robust Uncertainty Quantification Under Distribution Shifts: Shadi Alijani,

Homayoun Najjaran; [pdf] [arXiv]
[bibtex]
@InProceedings{Alijani_2025_CVPR, author = {Alijani, Shadi and Najjaran, Homayoun}, title = {WQLCP: Weighted Adaptive Conformal Prediction for Robust Uncertainty Quantification Under Distribution Shifts}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {1732-1741} }
The Surprising Utility of Group Partitioning in Improving Conformal Prediction of Visual Classifiers under Distributional Shifts: Kowshik Thopalli,

Vivek Narayanaswamy,

Jayaraman J. Thiagarajan; [pdf] [supp]
[bibtex]
@InProceedings{Thopalli_2025_CVPR, author = {Thopalli, Kowshik and Narayanaswamy, Vivek and Thiagarajan, Jayaraman J.}, title = {The Surprising Utility of Group Partitioning in Improving Conformal Prediction of Visual Classifiers under Distributional Shifts}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {1742-1751} }
Improving Optical Flow and Stereo Depth Estimation by Leveraging Uncertainty-Based Learning Difficulties: Jisoo Jeong,

Hong Cai,

Jamie Menjay Lin,

Fatih Porikli; [pdf] [arXiv]
[bibtex]
@InProceedings{Jeong_2025_CVPR, author = {Jeong, Jisoo and Cai, Hong and Lin, Jamie Menjay and Porikli, Fatih}, title = {Improving Optical Flow and Stereo Depth Estimation by Leveraging Uncertainty-Based Learning Difficulties}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {1712-1721} }