Publications

@inproceedings{SSBC2026,

title = {Label-Efficient Sclera Segmentation with Foundation Models: SSBC 2026},

author = {M. Vitek and D.D. Premani and A. Das and U.N. Modi and M.S. Raval and H.H. Bhatt and P. Baumstimler and Z.A. Daniels and A.H. Sheth and M. Gondalia and K.J. Shah and C. Zhang and C. Wang and A. Shin and K. Shigematsu and H. Shirono and K. Inoue and G. Gupta and A. Gupta and G. Sharma and T. Gupta and A. Nigam and R. Ramachandra and J. Nourmohammadi Khiarak and T. Akbari Saeed and F. Nourmohammadi Khiarak and A. Kumar and U. Pal and P. Peer and V. Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2026/09/IJCB_SSBC_2026.pdf},

year  = {2026},

date = {2026-09-01},

urldate = {2026-09-01},

booktitle = {Proceedings of the IEEE/IAPR International Joint Conference on Biometrics (IJCB)},

pages = {1--13},

abstract = {This paper presents a summary of the 2026 Sclera Segmentation Benchmarking Competition (SSBC), which focused on the adaptation of foundation models for the task of sclera segmentation and the implementation of label-efficient training paradigms.~The goal of the competition was to evaluate whether massive, generalized architectures can surpass domain-specific segmentation networks, and to assess the capacity of label-efficient strategies to overcome severe data scarcity. The competition featured two tracks, i.e.: (1) the Foundation Model Adaptation track, which provided fully annotated training data to adapt pre-trained (foundation) backbones, and (2) the Label-Efficient Learning track, which restricted access to ground truth annotations but supplied a massive collection of unlabelled imagery for training arbitrary sclera segmentation models, not just foundation model. The submitted approaches employed a variety of architectural designs, including parameter-efficient adaptations, vision-language guidance, and semi-supervised multi-architecture ensembles. To score the competition entries, experiments were conducted across three sequestered evaluation datasets containing real-world and synthetic images collected under diverse conditions. Results show that label-efficient methodologies can achieve remarkable accuracy, with the top Track 2 model performing comparably to the fully supervised Track 1 winner. Moreover, comparisons with SSBC 2025 results suggest that properly (domain) adapted foundation backbones significantly outperform previous approaches under the same training/evaluation protocol and thus represent a new state-of-the-art in sclera segmentation.},

keywords = {biometrics, competition IJCB, sclera, sclera segmentation, SSBC},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{SSBC25,

title = {Privacy-enhancing Sclera Segmentation Benchmarking Competition: SSBC 2025},

author = {Vitek, Matej and Tomašević, Darian and Das, Abhijit and Nathan, Sabari and Özbulak, Gökhan and Tataroğlu Özbulak and Gözde Ayşe and Calbimonte, Jean-Paul and Anjos, André and Bhatt, Hariohm Hemant and Premani, Dhruv Dhirendra and Chaudhari, Jay and Wang, Caiyong and Jiang, Jian and Zhang, Chi and Zhang, Qi and Ganapathi, Iyyakutti Iyappan and Ali, Syed Sadaf and Velayudan, Divya and Assefa, Maregu and Werghi, Naoufel and Daniels, Zachary A. and John, Leeon and Vyas, Ritesh and Khiarak, Jalil Nourmohammadi and Saeed, Taher Akbari and Nasehi, Mahsa and Kianfar, Ali and Pashazadeh Panahi, Mobina and Sharma, Geetanjali and Panth, Pushp Raj and Ramachandra, Raghavendra and Nigam, Aditya and Pal, Umapada and Peer, Peter and Štruc, Vitomir},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2025/08/IJCB_SSBC_25.pdf},

year  = {2025},

date = {2025-09-08},

booktitle = {Proceedings of the IEEE International Joint Conference on Biometrics (IJCB 2025)},

pages = {1--13},

publisher = {IEEE},

keywords = {biometrics, deep learning, sclera segmentation, segmentation, SSBC},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{SSBC2020,

title = {SSBC 2020: Sclera Segmentation Benchmarking Competition in the Mobile Environment},

author = {M. Vitek and A. Das and Y. Pourcenoux and A. Missler and C. Paumier and S. Das and I. De Ghosh and D. R. Lucio and L. A. Zanlorensi Jr. and D. Menotti and F. Boutros and N. Damer and J. H. Grebe and A. Kuijper and J. Hu and Y. He and C. Wang and H. Liu and Y. Wang and Z. Sun and D. Osorio-Roig and C. Rathgeb and C. Busch and J. Tapia and A.~Valenzuela and G. Zampoukis and L. Tsochatzidis and I. Pratikakis and S. Nathan and R. Suganya and V. Mehta and A. Dhall and K. Raja and G. Gupta and J. N. Khiarak and M. Akbari-Shahper and F. Jaryani and M. Asgari-Chenaghlu and R. Vyas and S. Dakshit and S. Dakshit and P. Peer and U. Pal and V. Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2020/11/IJCB_SSBC_2020.pdf},

year  = {2020},

date = {2020-09-28},

booktitle = {International Joint Conference on Biometrics (IJCB 2020)},

pages = {1--10},

abstract = {The paper presents a summary of the 2020 Sclera Segmentation Benchmarking Competition (SSBC), the 7th in the series of group benchmarking efforts centred around the problem of sclera segmentation. Different from previous editions, the goal of SSBC 2020 was to evaluate the performance of sclera-segmentation models on images captured with mobile devices. The competition was used as a platform to assess the sensitivity of existing models to i) differences in mobile devices used for image capture and ii) changes in the ambient acquisition conditions. 26 research groups registered for SSBC 2020, out of which 13 took part in the final round and submitted a total of 16 segmentation models for scoring. These included a wide variety of deep-learning solutions as well as one approach based on standard image processing techniques. Experiments were conducted with three recent datasets. Most of the segmentation models achieved relatively consistent  performance across images captured with different mobile devices (with slight differences across devices), but struggled most with  low-quality images captured in challenging ambient conditions, i.e., in an indoor environment and with poor lighting. },

keywords = {biometrics, competition IJCB, ocular, sclera, segmentation, SSBC},

pubstate = {published},

tppubtype = {inproceedings}

}