探究分割模型能否天然估算概率，发现其本身已有较强概率估计能力。
Deep Probability Segmentation: Are segmentation models probability estimators?
- 用校准概率估计方法测试分割模型的概率输出能力
- 校准后准确率提升但效果弱于分类任务
- 适合需要精准不确定性评估的场景
深度学习在多个领域实现高精度预测与估计。概率预测是其中重要方向，即模型估计事件发生的概率而非确定性结果。这一思路在分割任务中仍待探索，因图像中每个像素需分类。传统模型常忽略标签的概率性质，而准确的不确定性估计对提升模型可靠性至关重要。本研究将校准概率估计（CaPE）应用于分割任务，评估其对模型校准的影响。结果表明，尽管CaPE改善了校准效果，但其作用较分类任务弱，提示分割模型本身具备更强的概率估计能力。我们还分析了数据集规模和分箱优化对校准效果的影响。研究强调了分割模型作为概率估计器的表达能力，并引入概率推理机制，这对需要精确不确定性量化应用具有重要意义。
原文摘要 · Abstract (English)
Deep learning has revolutionized various fields by enabling highly accurate predictions and estimates. One important application is probabilistic prediction, where models estimate the probability of events rather than deterministic outcomes. This approach is particularly relevant and, therefore, still unexplored for segmentation tasks where each pixel in an image needs to be classified. Conventional models often overlook the probabilistic nature of labels, but accurate uncertainty estimation is crucial for improving the reliability and applicability of models. In this study, we applied Calibrated Probability Estimation (CaPE) to segmentation tasks to evaluate its impact on model calibration. Our results indicate that while CaPE improves calibration, its effect is less pronounced compared to classification tasks, suggesting that segmentation models can inherently provide better probability estimates. We also investigated the influence of dataset size and bin optimization on the effectiveness of calibration. Our results emphasize the expressive power of segmentation models as probability estimators and incorporate probabilistic reasoning, which is crucial for applications requiring precise uncertainty quantification.
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。