2 papers
cs.CV2025
S^4M: Boosting Semi-Supervised Instance Segmentation with SAM
Heeji Yoon, Heeseong Shin, Eunbeen Hong +4
Semi-supervised instance segmentation poses challenges due to limited labeled data, causing difficulties in accurately localizing distinct object instances. Current teacher-student…
cs.CV2024
SPACE: SPAtial-aware Consistency rEgularization for anomaly detection in Industrial applications
Daehwan Kim, Hyungmin Kim, Daun Jeong +2
In this paper, we propose SPACE, a novel anomaly detection methodology that integrates a Feature Encoder (FE) into the structure of the Student-Teacher method. The proposed method…