Label-efficient Machine Learning

1. Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation

2. Weakly Supervised Semantic Segmentation via Alternate Self-Dual Teaching

3. RankMatch: Fostering Confidence and Consistency in Learning with Noisy Labels

4. Reliable Mutual Distillation for Medical Image Segmentation under Imperfect Annotations

5. Gradient-Rebalanced Uncertainty Minimization for Cross-Site Adaptation of Medical Image Segmentation

6. Double-Check Soft Teacher for Semi-Supervised Object Detection

In the semi-supervised object detection task, due to the scarcity of labeled data and the diversity and complexity of objects to be detected, the quality of pseudo-labels generated by existing methods for unlabeled data is relatively low, which …

7. Cross-level Contrastive Learning and Consistency Constraint for Semi-supervised Medical Image Segmentation

8. Interactive Dual-Model Learning for Semi-supervised Medical Image Segmentation (in Chinese)

9. Weakly Supervised Disease Localization in Chest X-rays via Looking into Image Relations

10. Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning

Open-set semi-supervised learning~(open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data. While the mainstream technique seeks to completely filter out the OOD …