CVPR 2024 Open Access Repository

The Fifth Workshop on Fair Data-Efficient and Trusted Computer Vision

Data-free Defense of Black Box Models Against Adversarial Attacks: Gaurav Kumar Nayak,

Inder Khatri,

Ruchit Rawal,

Anirban Chakraborty; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nayak_2024_CVPR, author = {Nayak, Gaurav Kumar and Khatri, Inder and Rawal, Ruchit and Chakraborty, Anirban}, title = {Data-free Defense of Black Box Models Against Adversarial Attacks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {254-263} }
Improving the Robustness of 3D Human Pose Estimation: A Benchmark and Learning from Noisy Input: Trung-Hieu Hoang,

Mona Zehni,

Huy Phan,

Duc Minh Vo,

Minh N. Do; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hoang_2024_CVPR, author = {Hoang, Trung-Hieu and Zehni, Mona and Phan, Huy and Vo, Duc Minh and Do, Minh N.}, title = {Improving the Robustness of 3D Human Pose Estimation: A Benchmark and Learning from Noisy Input}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {113-123} }
Practical Region-level Attack against Segment Anything Models: Yifan Shen,

Zhengyuan Li,

Gang Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Shen_2024_CVPR, author = {Shen, Yifan and Li, Zhengyuan and Wang, Gang}, title = {Practical Region-level Attack against Segment Anything Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {194-203} }
AR-CP: Uncertainty-Aware Perception in Adverse Conditions with Conformal Prediction and Augmented Reality For Assisted Driving: Achref Doula,

Max Mühlhäuser,

Alejandro Sanchez Guinea; [pdf]
[bibtex]
@InProceedings{Doula_2024_CVPR, author = {Doula, Achref and M\"uhlh\"auser, Max and Guinea, Alejandro Sanchez}, title = {AR-CP: Uncertainty-Aware Perception in Adverse Conditions with Conformal Prediction and Augmented Reality For Assisted Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {216-226} }
T2FNorm: Train-time Feature Normalization for OOD Detection in Image Classification: Sudarshan Regmi,

Bibek Panthi,

Sakar Dotel,

Prashnna K Gyawali,

Danail Stoyanov,

Binod Bhattarai; [pdf] [supp]
[bibtex]
@InProceedings{Regmi_2024_CVPR, author = {Regmi, Sudarshan and Panthi, Bibek and Dotel, Sakar and Gyawali, Prashnna K and Stoyanov, Danail and Bhattarai, Binod}, title = {T2FNorm: Train-time Feature Normalization for OOD Detection in Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {153-162} }
SkipPLUS: Skip the First Few Layers to Better Explain Vision Transformers: Faridoun Mehri,

Mohsen Fayyaz,

Mahdieh Soleymani Baghshah,

Mohammad Taher Pilehvar; [pdf] [supp]
[bibtex]
@InProceedings{Mehri_2024_CVPR, author = {Mehri, Faridoun and Fayyaz, Mohsen and Baghshah, Mahdieh Soleymani and Pilehvar, Mohammad Taher}, title = {SkipPLUS: Skip the First Few Layers to Better Explain Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {204-215} }
Fast-NTK: Parameter-Efficient Unlearning for Large-Scale Models: Guihong Li,

Hsiang Hsu,

Chun-Fu Chen,

Radu Marculescu; [pdf]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Guihong and Hsu, Hsiang and Chen, Chun-Fu and Marculescu, Radu}, title = {Fast-NTK: Parameter-Efficient Unlearning for Large-Scale Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {227-234} }
Robust and Explainable Fine-Grained Visual Classification with Transfer Learning: A Dual-Carriageway Framework: Zheming Zuo,

Joseph Smith,

Jonathan Stonehouse,

Boguslaw Obara; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zuo_2024_CVPR, author = {Zuo, Zheming and Smith, Joseph and Stonehouse, Jonathan and Obara, Boguslaw}, title = {Robust and Explainable Fine-Grained Visual Classification with Transfer Learning: A Dual-Carriageway Framework}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {183-193} }
DIA: Diffusion based Inverse Network Attack on Collaborative Inference: Dake Chen,

Shiduo Li,

Yuke Zhang,

Chenghao Li,

Souvik Kundu,

Peter A. Beerel; [pdf]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Dake and Li, Shiduo and Zhang, Yuke and Li, Chenghao and Kundu, Souvik and Beerel, Peter A.}, title = {DIA: Diffusion based Inverse Network Attack on Collaborative Inference}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {124-130} }
Our Deep CNN Face Matchers Have Developed Achromatopsia: Aman Bhatta,

Domingo Mery,

Haiyu Wu,

Joyce Annan,

Michael C. King,

Kevin W. Bowyer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bhatta_2024_CVPR, author = {Bhatta, Aman and Mery, Domingo and Wu, Haiyu and Annan, Joyce and King, Michael C. and Bowyer, Kevin W.}, title = {Our Deep CNN Face Matchers Have Developed Achromatopsia}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {142-152} }
Mitigating Bias Using Model-Agnostic Data Attribution: Sander De Coninck,

Sam Leroux,

Pieter Simoens; [pdf] [arXiv]
[bibtex]
@InProceedings{De_Coninck_2024_CVPR, author = {De Coninck, Sander and Leroux, Sam and Simoens, Pieter}, title = {Mitigating Bias Using Model-Agnostic Data Attribution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {235-243} }
Fractals as Pre-training Datasets for Anomaly Detection and Localization: Cynthia I. Ugwu,

Sofia Casarin,

Oswald Lanz; [pdf] [arXiv]
[bibtex]
@InProceedings{Ugwu_2024_CVPR, author = {Ugwu, Cynthia I. and Casarin, Sofia and Lanz, Oswald}, title = {Fractals as Pre-training Datasets for Anomaly Detection and Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {163-172} }
Enforcing Conditional Independence for Fair Representation Learning and Causal Image Generation: Jensen Hwa,

Qingyu Zhao,

Aditya Lahiri,

Adnan Masood,

Babak Salimi,

Ehsan Adeli; [pdf] [arXiv]
[bibtex]
@InProceedings{Hwa_2024_CVPR, author = {Hwa, Jensen and Zhao, Qingyu and Lahiri, Aditya and Masood, Adnan and Salimi, Babak and Adeli, Ehsan}, title = {Enforcing Conditional Independence for Fair Representation Learning and Causal Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {103-112} }
Test-time Assessment of a Model's Performance on Unseen Domains via Optimal Transport: Akshay Mehra,

Yunbei Zhang,

Jihun Hamm; [pdf]
[bibtex]
@InProceedings{Mehra_2024_CVPR, author = {Mehra, Akshay and Zhang, Yunbei and Hamm, Jihun}, title = {Test-time Assessment of a Model's Performance on Unseen Domains via Optimal Transport}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {173-182} }
Towards Explainable Visual Vessel Recognition Using Fine-Grained Classification and Image Retrieval: Heiko Karus,

Friedhelm Schwenker,

Michael Munz,

Michael Teutsch; [pdf]
[bibtex]
@InProceedings{Karus_2024_CVPR, author = {Karus, Heiko and Schwenker, Friedhelm and Munz, Michael and Teutsch, Michael}, title = {Towards Explainable Visual Vessel Recognition Using Fine-Grained Classification and Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {82-92} }
Towards Efficient Machine Unlearning with Data Augmentation: Guided Loss-Increasing (GLI) to Prevent the Catastrophic Model Utility Drop: Dasol Choi,

Soora Choi,

Eunsun Lee,

Jinwoo Seo,

Dongbin Na; [pdf] [supp]
[bibtex]
@InProceedings{Choi_2024_CVPR, author = {Choi, Dasol and Choi, Soora and Lee, Eunsun and Seo, Jinwoo and Na, Dongbin}, title = {Towards Efficient Machine Unlearning with Data Augmentation: Guided Loss-Increasing (GLI) to Prevent the Catastrophic Model Utility Drop}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {93-102} }
ReweightOOD: Loss Reweighting for Distance-based OOD Detection: Sudarshan Regmi,

Bibek Panthi,

Yifei Ming,

Prashnna K Gyawali,

Danail Stoyanov,

Binod Bhattarai; [pdf] [supp]
[bibtex]
@InProceedings{Regmi_2024_CVPR, author = {Regmi, Sudarshan and Panthi, Bibek and Ming, Yifei and Gyawali, Prashnna K and Stoyanov, Danail and Bhattarai, Binod}, title = {ReweightOOD: Loss Reweighting for Distance-based OOD Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {131-141} }
RLNet: Robust Linearized Networks for Efficient Private Inference: Sreetama Sarkar,

Souvik Kundu,

Peter A. Beerel; [pdf]
[bibtex]
@InProceedings{Sarkar_2024_CVPR, author = {Sarkar, Sreetama and Kundu, Souvik and Beerel, Peter A.}, title = {RLNet: Robust Linearized Networks for Efficient Private Inference}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {244-253} }