CVPR 2025 Open Access Repository

Domain Generalization: Evolution, Breakthroughs, and Future Horizons

VISTA-CLIP: Visual Incremental Self-Tuned Adaptation for Efficient Continual Panoptic Segmentation: Manjunath D,

Shrikar Madhu,

Aniruddh Sikdar,

Suresh Sundaram; [pdf]
[bibtex]
@InProceedings{D_2025_CVPR, author = {D, Manjunath and Madhu, Shrikar and Sikdar, Aniruddh and Sundaram, Suresh}, title = {VISTA-CLIP: Visual Incremental Self-Tuned Adaptation for Efficient Continual Panoptic Segmentation}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6555-6563} }
MoPEFT: A Mixture-of-PEFTs for the Segment Anything Model: Rajat Sahay,

Andreas Savakis; [pdf] [arXiv]
[bibtex]
@InProceedings{Sahay_2025_CVPR, author = {Sahay, Rajat and Savakis, Andreas}, title = {MoPEFT: A Mixture-of-PEFTs for the Segment Anything Model}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6500-6510} }
Prototype-Based Continual Learning with Label-free Replay Buffer and Cluster Preservation Loss: Agil Aghasanli,

Yi Li,

Plamen Angelov; [pdf] [arXiv]
[bibtex]
@InProceedings{Aghasanli_2025_CVPR, author = {Aghasanli, Agil and Li, Yi and Angelov, Plamen}, title = {Prototype-Based Continual Learning with Label-free Replay Buffer and Cluster Preservation Loss}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6545-6554} }
Mixture-of-Shape-Experts (MoSE): End-to-End Shape Dictionary Framework to Prompt SAM for Generalizable Medical Segmentation: Jia Wei,

Xiaoqi Zhao,

Jonghye Woo,

Jinsong Ouyang,

Georges El Fakhri,

Qingyu Chen,

Xiaofeng Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Wei_2025_CVPR, author = {Wei, Jia and Zhao, Xiaoqi and Woo, Jonghye and Ouyang, Jinsong and El Fakhri, Georges and Chen, Qingyu and Liu, Xiaofeng}, title = {Mixture-of-Shape-Experts (MoSE): End-to-End Shape Dictionary Framework to Prompt SAM for Generalizable Medical Segmentation}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6448-6458} }
Task-conditioned Ensemble of Expert Models for Continuous Learning: Renu Sharma,

Debasmita Pal,

Arun Ross; [pdf] [arXiv]
[bibtex]
@InProceedings{Sharma_2025_CVPR, author = {Sharma, Renu and Pal, Debasmita and Ross, Arun}, title = {Task-conditioned Ensemble of Expert Models for Continuous Learning}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6479-6488} }
Domain Generalization through Attenuation of Domain-Specific Information: Reiji Saito,

Kazuhiro Hotta; [pdf] [arXiv]
[bibtex]
@InProceedings{Saito_2025_CVPR, author = {Saito, Reiji and Hotta, Kazuhiro}, title = {Domain Generalization through Attenuation of Domain-Specific Information}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6459-6468} }
PiCaZo: Pixel-Aligned Contrastive Learning for Zero-Shot Domain Adaptation: Aniruddh Sikdar,

Arya Kishor,

Ishika Kadam,

Suresh Sundaram; [pdf]
[bibtex]
@InProceedings{Sikdar_2025_CVPR, author = {Sikdar, Aniruddh and Kishor, Arya and Kadam, Ishika and Sundaram, Suresh}, title = {PiCaZo: Pixel-Aligned Contrastive Learning for Zero-Shot Domain Adaptation}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6534-6544} }
FM-LoRA: Factorized Low-Rank Meta-Prompting for Continual Learning: Xiaobing Yu,

Jin Yang,

Xiao Wu,

Peijie Qiu,

Xiaofeng Liu; [pdf]
[bibtex]
@InProceedings{Yu_2025_CVPR, author = {Yu, Xiaobing and Yang, Jin and Wu, Xiao and Qiu, Peijie and Liu, Xiaofeng}, title = {FM-LoRA: Factorized Low-Rank Meta-Prompting for Continual Learning}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6409-6418} }
IMC: A Benchmark for Invariant Learning under Multiple Causes: Taero Kim,

Seonggyun Lee,

Joonseong Kang,

Youngjun Choi,

Wonsang Yun,

Nicole Hee-Yeon Kim,

Ziyu Chen,

Lexing Xie,

Kyungwoo Song; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2025_CVPR, author = {Kim, Taero and Lee, Seonggyun and Kang, Joonseong and Choi, Youngjun and Yun, Wonsang and Kim, Nicole Hee-Yeon and Chen, Ziyu and Xie, Lexing and Song, Kyungwoo}, title = {IMC: A Benchmark for Invariant Learning under Multiple Causes}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6469-6478} }
PhysNav-DG: A Novel Adaptive Framework for Robust VLM-Sensor Fusion in Navigation Applications: Trisanth Srinivasan,

Santosh Patapati; [pdf]
[bibtex]
@InProceedings{Srinivasan_2025_CVPR, author = {Srinivasan, Trisanth and Patapati, Santosh}, title = {PhysNav-DG: A Novel Adaptive Framework for Robust VLM-Sensor Fusion in Navigation Applications}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6564-6572} }
Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning: Yusaku Takama,

Ning Ding,

Tatsuya Yokota,

Toru Tamaki; [pdf]
[bibtex]
@InProceedings{Takama_2025_CVPR, author = {Takama, Yusaku and Ding, Ning and Yokota, Tatsuya and Tamaki, Toru}, title = {Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6429-6437} }
ARDGen: Augmentation Regularization for Domain-Generalized Medical Report Generation: Syed Bilal Ahsan,

Muhammad Ikhalas,

Muhammad Muzamil Khan,

Sana Ullah,

Muhammad Zaigham Zaheer; [pdf]
[bibtex]
@InProceedings{Ahsan_2025_CVPR, author = {Ahsan, Syed Bilal and Ikhalas, Muhammad and Khan, Muhammad Muzamil and Ullah, Sana and Zaheer, Muhammad Zaigham}, title = {ARDGen: Augmentation Regularization for Domain-Generalized Medical Report Generation}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6524-6533} }
Improving Open-World Object Localization by Discovering Background: Ashish Singh,

Michael Jones,

Kuan-Chuan Peng,

Anoop Cherian,

Moitreya Chatterjee,

Erik Learned-Miller; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Singh_2025_CVPR, author = {Singh, Ashish and Jones, Michael and Peng, Kuan-Chuan and Cherian, Anoop and Chatterjee, Moitreya and Learned-Miller, Erik}, title = {Improving Open-World Object Localization by Discovering Background}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6438-6447} }
Confidence-calibrated covariate shift correction for few-shot classification in Vision-Language Models: Behraj Khan,

Rizwan Qureshi,

Nouman Muhammad Durrani,

Tahir Qasim Syed; [pdf] [arXiv]
[bibtex]
@InProceedings{Khan_2025_CVPR, author = {Khan, Behraj and Qureshi, Rizwan and Durrani, Nouman Muhammad and Syed, Tahir Qasim}, title = {Confidence-calibrated covariate shift correction for few-shot classification in Vision-Language Models}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6511-6523} }
T-SAM: Transductive Learning for Segment Anything Model: Rangel Daroya,

Deepak Chandran,

Subhransu Maji,

Andrea Fanelli; [pdf]
[bibtex]
@InProceedings{Daroya_2025_CVPR, author = {Daroya, Rangel and Chandran, Deepak and Maji, Subhransu and Fanelli, Andrea}, title = {T-SAM: Transductive Learning for Segment Anything Model}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6419-6428} }
Task-Level Contrastiveness for Cross-Domain Few-Shot Learning: Kristi Topollai,

Anna Choromanska; [pdf]
[bibtex]
@InProceedings{Topollai_2025_CVPR, author = {Topollai, Kristi and Choromanska, Anna}, title = {Task-Level Contrastiveness for Cross-Domain Few-Shot Learning}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {6489-6499} }