Seunghyeok Hyun
Research Subjects
Seunghyeok Hyun has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Jongwon Kim
School of Integrated Technology, Gwangju Institute of Science and Technology, Gwangju 61005, Korea
2 shared publications - Kyoobin Lee
Department of AI Convergence, Gwangju Institute of Science and Technology (GIST), Gwangju, Republic of Korea
2 shared publications - Seongju Lee
Gwangju Institute of Science and Technology (GIST)
2 shared publications - Yeonguk Yu
Gwangju Institute of Science and Technology (GIST)
2 shared publications - Youmin Park2 shared publications
- Yunjae Heo2 shared publications
Latest Publications
- Open Access
- 15 July 2026
- Published by Elsevier in Intelligent Systems with Applications
- Vol. 31
Human-efficient annotation system via active semi-supervised learning and selective review
- 15 July 2026
- Published by Elsevier in Intelligent Systems with Applications
- Vol. 31
Open AccessHuman-efficient annotation system via active semi-supervised learning and selective review
- Open Access
- 9 April 2026
- Published by Elsevier in SSRN Electronic Journal
Human-Efficient Annotation System via Active Semi Supervised Learning and Selective Review
Building training datasets for perception systems in autonomous driving and industrial inspection requires large volumes of pixel-level annotations, and the annotation cost increases with scene complexity and the number of object categories. Existing annotation platforms combine foundation models with active learning, and some offer confidence-based filtering. However, existing systems do not account for the class imbalance that arises during iterative label pool expansion, nor study how semi-supervised learning (SSL), calibration, and selective review interact across annotation rounds. We propose an annotation system that reduces the manual annotation effort through calibrated confidence scores: predictions below a minimum threshold are discarded, high-confidence predictions are accepted without human review, and the remaining uncertain predictions are flagged for manual inspection. A controlled annotation experiment on Cityscapes shows that the system reduces human annotation time by 1.9x and improves Average Precision (AP) by 1.8 points over an active-learning baseline with Mask2Former and SAM 2, while auto-accepting 74.3% of predictions with 85.8% precision at the final round. An offline ablation shows that SSL and calibration jointly reduce false positives by 40.4%, with auto-accept precision improving across rounds rather than declining under supervised-only training. Compared to unassisted manual polygon labeling, the proposed system reduces human annotation time by 3.2x while improving AP by 4.5 points under the same 150-image budget.
- 9 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessHuman-Efficient Annotation System via Active Semi Supervised Learning and Selective Review
Building training datasets for perception systems in autonomous driving and industrial inspection requires large volumes of pixel-level annotations, and the annotation cost increases with scene complexity and the number of object categories. Existing annotation platforms combine foundation models with active learning, and some offer confidence-based filtering. However, existing systems do not account for the class imbalance that arises during iterative label pool expansion, nor study how semi-supervised learning (SSL), calibration, and selective review interact across annotation rounds. We propose an annotation system that reduces the manual annotation effort through calibrated confidence scores: predictions below a minimum threshold are discarded, high-confidence predictions are accepted without human review, and the remaining uncertain predictions are flagged for manual inspection. A controlled annotation experiment on Cityscapes shows that the system reduces human annotation time by 1.9x and improves Average Precision (AP) by 1.8 points over an active-learning baseline with Mask2Former and SAM 2, while auto-accepting 74.3% of predictions with 85.8% precision at the final round. An offline ablation shows that SSL and calibration jointly reduce false positives by 40.4%, with auto-accept precision improving across rounds rather than declining under supervised-only training. Compared to unassisted manual polygon labeling, the proposed system reduces human annotation time by 3.2x while improving AP by 4.5 points under the same 150-image budget.