对比卷积与注意力模型在牙齿分割中的表现，发现标签瑕疵影响预测质量。
Segmentation of Bovid Dentition Under Imperfect Annotations: A Comparative Study of Convolutional and Attention Models
- 用卷积和视觉变压器对比分割牛牙图像，评估不同预处理对标签瑕疵的影响。
- 预处理对Dice和mIoU等指标提升有限，但显著改善了分割结果的视觉质量。
- 适合关注医学图像分割中标签噪声问题的研究者或实际应用开发者。
语义分割将图像分解为对应不同对象类别的掩码区域，如人、车、标志或建筑。机器学习的进步使该任务从传统的基于规则的启发式方法（如边缘检测）转向深度神经网络（DNN），直接学习像素分类。然而，语义分割DNN严重依赖专家设计的掩码目标进行训练，不完美或错位的掩码会干扰模型的有效学习。本文针对高分辨率牛牙照片数据集B.O.V.I.D.（包含手工制作的分割掩码，非专为机器学习设计）开展对比研究，评估从卷积主干到视觉变换器的各种分割架构，并测试多种预处理与对齐技术以缓解标签缺陷。研究发现，尽管这些预处理手段对Dice分数和平均交并比（mIoU）等定量指标影响较小，但其对预测掩码的定性效果具有显著提升。
原文摘要 · Abstract (English)
Semantic segmentation decomposes an image into distinct mask regions corresponding to different object categories, such as people, cars, signs or buildings. Advances in machine learning (ML) have shifted this task away from traditional rule-based heuristics such as edge detection, towards deep neural networks (DNN) that learn to classify pixels directly. However, semantic segmentation DNNs crucially depend on expertly designed mask targets to learn from, and imperfect or misaligned masks can interfere with a model's ability to learn effectively. This paper presents a comparative study of segmentation architectures, ranging from convolutional backbones to vision transformers, applied to the B.O.V.I.D. dataset, a corpus of high-resolution bovid dental photographs paired with hand-made segmentation masks not originally designed for ML-based training. We evaluate a range of preprocessing and alignment techniques to mitigate the resulting label imperfections. We find that while these preprocessing choices have limited effect on quantitative metrics such as Dice score and mIoU, their qualitative impact on predicted masks is substantial.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。