CVPR 2024 Open Access Repository

The 3rd Explainable AI for Computer Vision (XAI4CV) Workshop

PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits: Maximilian Dreyer,

Erblina Purelku,

Johanna Vielhaben,

Wojciech Samek,

Sebastian Lapuschkin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dreyer_2024_CVPR, author = {Dreyer, Maximilian and Purelku, Erblina and Vielhaben, Johanna and Samek, Wojciech and Lapuschkin, Sebastian}, title = {PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8212-8217} }
Allowing Humans to Interactively Guide Machines Where to Look Does Not Always Improve Human-AI Team's Classification Accuracy: Giang Nguyen,

Mohammad Reza Taesiri,

Sunnie S. Y. Kim,

Anh Nguyen; [pdf] [supp]
[bibtex]
@InProceedings{Nguyen_2024_CVPR, author = {Nguyen, Giang and Taesiri, Mohammad Reza and Kim, Sunnie S. Y. and Nguyen, Anh}, title = {Allowing Humans to Interactively Guide Machines Where to Look Does Not Always Improve Human-AI Team's Classification Accuracy}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8169-8175} }
SUNY: A Visual Interpretation Framework for Convolutional Neural Networks from a Necessary and Sufficient Perspective: Xiwei Xuan,

Ziquan Deng,

Hsuan-Tien Lin,

Zhaodan Kong,

Kwan-Liu Ma; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xuan_2024_CVPR, author = {Xuan, Xiwei and Deng, Ziquan and Lin, Hsuan-Tien and Kong, Zhaodan and Ma, Kwan-Liu}, title = {SUNY: A Visual Interpretation Framework for Convolutional Neural Networks from a Necessary and Sufficient Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8371-8376} }
Explaining Models Relating Objects and Privacy: Alessio Xompero,

Myriam Bontonou,

Jean-Michel Arbona,

Emmanouil Benetos,

Andrea Cavallaro; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xompero_2024_CVPR, author = {Xompero, Alessio and Bontonou, Myriam and Arbona, Jean-Michel and Benetos, Emmanouil and Cavallaro, Andrea}, title = {Explaining Models Relating Objects and Privacy}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8194-8198} }
LVLM-Intrepret: An Interpretability Tool for Large Vision-Language Models: Gabriela Ben Melech Stan,

Estelle Aflalo,

Raanan Yehezkel Rohekar,

Anahita Bhiwandiwalla,

Shao-Yen Tseng,

Matthew Lyle Olson,

Yaniv Gurwicz,

Chenfei Wu,

Nan Duan,

Vasudev Lal; [pdf]
[bibtex]
@InProceedings{Ben_Melech_Stan_2024_CVPR, author = {Ben Melech Stan, Gabriela and Aflalo, Estelle and Rohekar, Raanan Yehezkel and Bhiwandiwalla, Anahita and Tseng, Shao-Yen and Olson, Matthew Lyle and Gurwicz, Yaniv and Wu, Chenfei and Duan, Nan and Lal, Vasudev}, title = {LVLM-Intrepret: An Interpretability Tool for Large Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8182-8187} }
Exploring Explainability in Video Action Recognition: Avinab Saha,

Shashank Gupta,

Sravan Kumar Ankireddy,

Karl Chahine,

Joydeep Ghosh; [pdf] [arXiv]
[bibtex]
@InProceedings{Saha_2024_CVPR, author = {Saha, Avinab and Gupta, Shashank and Ankireddy, Sravan Kumar and Chahine, Karl and Ghosh, Joydeep}, title = {Exploring Explainability in Video Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8176-8181} }
Recent Trends Challenges and Limitations of Explainable AI in Remote Sensing: Adrian Höhl,

Ivica Obadic,

Miguel-Ángel Fernández-Torres,

Dario Oliveira,

Xiao Xiang Zhu; [pdf] [supp]
[bibtex]
@InProceedings{Hohl_2024_CVPR, author = {H\"ohl, Adrian and Obadic, Ivica and Fern\'andez-Torres, Miguel-\'Angel and Oliveira, Dario and Zhu, Xiao Xiang}, title = {Recent Trends Challenges and Limitations of Explainable AI in Remote Sensing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8199-8205} }
Quantifying Explainability with Multi-Scale Gaussian Mixture Models: Anthony Rhodes,

Yali Bian,

Ilke Demir; [pdf]
[bibtex]
@InProceedings{Rhodes_2024_CVPR, author = {Rhodes, Anthony and Bian, Yali and Demir, Ilke}, title = {Quantifying Explainability with Multi-Scale Gaussian Mixture Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8223-8228} }
Semantic Approach to Quantifying the Consistency of Diffusion Model Image Generation: Brinnae Bent; [pdf] [arXiv]
[bibtex]
@InProceedings{Bent_2024_CVPR, author = {Bent, Brinnae}, title = {Semantic Approach to Quantifying the Consistency of Diffusion Model Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8218-8222} }
ReciproCAM: Lightweight Gradient-free Class Activation Map for Post-hoc Explanations: Seok-Yong Byun,

Wonju Lee; [pdf]
[bibtex]
@InProceedings{Byun_2024_CVPR, author = {Byun, Seok-Yong and Lee, Wonju}, title = {ReciproCAM: Lightweight Gradient-free Class Activation Map for Post-hoc Explanations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8364-8370} }
Spatial Sensitive Grad-CAM++: Improved Visual Explanation for Object Detectors via Weighted Combination of Gradient Map: Toshinori Yamauchi; [pdf]
[bibtex]
@InProceedings{Yamauchi_2024_CVPR, author = {Yamauchi, Toshinori}, title = {Spatial Sensitive Grad-CAM++: Improved Visual Explanation for Object Detectors via Weighted Combination of Gradient Map}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8164-8168} }
CA-Stream: Attention-based Pooling for Interpretable Image Recognition: Felipe Torres,

Hanwei Zhang,

Ronan Sicre,

Stéphane Ayache,

Yannis Avrithis; [pdf] [supp]
[bibtex]
@InProceedings{Torres_2024_CVPR, author = {Torres, Felipe and Zhang, Hanwei and Sicre, Ronan and Ayache, St\'ephane and Avrithis, Yannis}, title = {CA-Stream: Attention-based Pooling for Interpretable Image Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8206-8211} }
Interactive Visual Feature Search: Devon Ulrich,

Ruth Fong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ulrich_2024_CVPR, author = {Ulrich, Devon and Fong, Ruth}, title = {Interactive Visual Feature Search}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8188-8193} }