✨VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation

📝 Summary:
VQ-Seg introduces vector quantization to replace dropout with a controllable perturbation module for semi-supervised medical image segmentation. It uses a dual-branch architecture and foundation model guidance to maintain performance. VQ-Seg outperforms state-of-the-art methods on various medical...

🔹 Publication Date: Published on Jan 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.10124
• PDF: https://arxiv.org/pdf/2601.10124
• Project Page: https://github.com/script-Yang/VQ-Seg
• Github: https://github.com/script-Yang/VQ-Seg

✨ Datasets citing this paper:
• https://huggingface.co/datasets/yscript/ACDC-PNG

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#MedicalImageSegmentation #SemiSupervisedLearning #VectorQuantization #DeepLearning #ComputerVision

✨Multiscale Switch for Semi-Supervised and Contrastive Learning in Medical Ultrasound Image Segmentation

📝 Summary:
This paper introduces Switch, a semi-supervised learning framework for medical ultrasound segmentation. It uses multiscale patch mixing and frequency domain contrastive learning for robust features. Switch outperforms state-of-the-art methods and even fully supervised baselines using very little ...

🔹 Publication Date: Published on Mar 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.18655
• PDF: https://arxiv.org/pdf/2603.18655
• Github: https://github.com/jinggqu/Switch

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#MedicalImaging #ImageSegmentation #SemiSupervisedLearning #ContrastiveLearning #DeepLearning

✨Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization

📝 Summary:
Semi-DPO addresses label noise in multi-dimensional visual preference learning. It treats consistent data as clean and conflicting data as noisy, using iterative refinement via pseudo-labeling. This improves alignment with complex human preferences and achieves state-of-the-art results.

🔹 Publication Date: Published on Apr 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.24952
• PDF: https://arxiv.org/pdf/2604.24952
• Project Page: https://liming-ai.github.io/SemiDPO
• Github: https://liming-ai.github.io/SemiDPO

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#MachineLearning #SemiSupervisedLearning #DPO #NoisyData #PreferenceLearning