Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.10737 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908490037985280 |
|---|---|
| author | Vitek, Matej Tomašević, Darian Das, Abhijit Nathan, Sabari Özbulak, Gökhan Özbulak, Gözde Ayşe Tataroğlu Calbimonte, Jean-Paul Anjos, André Bhatt, Hariohm Hemant Premani, Dhruv Dhirendra Chaudhari, Jay Wang, Caiyong Jiang, Jian Zhang, Chi Zhang, Qi Ganapathi, Iyyakutti Iyappan Ali, Syed Sadaf Velayudan, Divya Assefa, Maregu Werghi, Naoufel Daniels, Zachary A. John, Leeon Vyas, Ritesh Khiarak, Jalil Nourmohammadi Saeed, Taher Akbari Nasehi, Mahsa Kianfar, Ali Panahi, Mobina Pashazadeh Sharma, Geetanjali Panth, Pushp Raj Ramachandra, Raghavendra Nigam, Aditya Pal, Umapada Peer, Peter Štruc, Vitomir |
| author_facet | Vitek, Matej Tomašević, Darian Das, Abhijit Nathan, Sabari Özbulak, Gökhan Özbulak, Gözde Ayşe Tataroğlu Calbimonte, Jean-Paul Anjos, André Bhatt, Hariohm Hemant Premani, Dhruv Dhirendra Chaudhari, Jay Wang, Caiyong Jiang, Jian Zhang, Chi Zhang, Qi Ganapathi, Iyyakutti Iyappan Ali, Syed Sadaf Velayudan, Divya Assefa, Maregu Werghi, Naoufel Daniels, Zachary A. John, Leeon Vyas, Ritesh Khiarak, Jalil Nourmohammadi Saeed, Taher Akbari Nasehi, Mahsa Kianfar, Ali Panahi, Mobina Pashazadeh Sharma, Geetanjali Panth, Pushp Raj Ramachandra, Raghavendra Nigam, Aditya Pal, Umapada Peer, Peter Štruc, Vitomir |
| contents | This paper presents a summary of the 2025 Sclera Segmentation Benchmarking Competition (SSBC), which focused on the development of privacy-preserving sclera-segmentation models trained using synthetically generated ocular images. The goal of the competition was to evaluate how well models trained on synthetic data perform in comparison to those trained on real-world datasets. The competition featured two tracks: $(i)$ one relying solely on synthetic data for model development, and $(ii)$ one combining/mixing synthetic with (a limited amount of) real-world data. A total of nine research groups submitted diverse segmentation models, employing a variety of architectural designs, including transformer-based solutions, lightweight models, and segmentation networks guided by generative frameworks. Experiments were conducted across three evaluation datasets containing both synthetic and real-world images, collected under diverse conditions. Results show that models trained entirely on synthetic data can achieve competitive performance, particularly when dedicated training strategies are employed, as evidenced by the top performing models that achieved $F_1$ scores of over $0.8$ in the synthetic data track. Moreover, performance gains in the mixed track were often driven more by methodological choices rather than by the inclusion of real data, highlighting the promise of synthetic data for privacy-aware biometric development. The code and data for the competition is available at: https://github.com/dariant/SSBC_2025. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_10737 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Privacy-enhancing Sclera Segmentation Benchmarking Competition: SSBC 2025 Vitek, Matej Tomašević, Darian Das, Abhijit Nathan, Sabari Özbulak, Gökhan Özbulak, Gözde Ayşe Tataroğlu Calbimonte, Jean-Paul Anjos, André Bhatt, Hariohm Hemant Premani, Dhruv Dhirendra Chaudhari, Jay Wang, Caiyong Jiang, Jian Zhang, Chi Zhang, Qi Ganapathi, Iyyakutti Iyappan Ali, Syed Sadaf Velayudan, Divya Assefa, Maregu Werghi, Naoufel Daniels, Zachary A. John, Leeon Vyas, Ritesh Khiarak, Jalil Nourmohammadi Saeed, Taher Akbari Nasehi, Mahsa Kianfar, Ali Panahi, Mobina Pashazadeh Sharma, Geetanjali Panth, Pushp Raj Ramachandra, Raghavendra Nigam, Aditya Pal, Umapada Peer, Peter Štruc, Vitomir Computer Vision and Pattern Recognition This paper presents a summary of the 2025 Sclera Segmentation Benchmarking Competition (SSBC), which focused on the development of privacy-preserving sclera-segmentation models trained using synthetically generated ocular images. The goal of the competition was to evaluate how well models trained on synthetic data perform in comparison to those trained on real-world datasets. The competition featured two tracks: $(i)$ one relying solely on synthetic data for model development, and $(ii)$ one combining/mixing synthetic with (a limited amount of) real-world data. A total of nine research groups submitted diverse segmentation models, employing a variety of architectural designs, including transformer-based solutions, lightweight models, and segmentation networks guided by generative frameworks. Experiments were conducted across three evaluation datasets containing both synthetic and real-world images, collected under diverse conditions. Results show that models trained entirely on synthetic data can achieve competitive performance, particularly when dedicated training strategies are employed, as evidenced by the top performing models that achieved $F_1$ scores of over $0.8$ in the synthetic data track. Moreover, performance gains in the mixed track were often driven more by methodological choices rather than by the inclusion of real data, highlighting the promise of synthetic data for privacy-aware biometric development. The code and data for the competition is available at: https://github.com/dariant/SSBC_2025. |
| title | Privacy-enhancing Sclera Segmentation Benchmarking Competition: SSBC 2025 |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.10737 |