Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogate
Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogate
复制标题
DOI：
10.1609/aaai.v36i9.21243
复制
发表时间：
2019-09
期刊：
影响因子：
--
通讯作者：
Lu Mi;Hao Wang;Yonglong Tian;Hao He;N. Shavit
中科院分区：
文献类型：
--
作者：
Lu Mi;Hao Wang;Yonglong Tian;Hao He;N. Shavit
不确定性估计是评估计算机视觉中深度学习模型鲁棒性的重要步骤，特别是在应用于风险敏感领域时。然而，大多数最先进的深度学习模型要么无法获得不确定性估计，要么需要进行重大修改（例如，大多数以前的方法都不能把一个任意的模型从货架上拿下来，产生不确定性估计，而不重新训练或重新设计它。为了解决这个差距，我们进行了系统的探索到训练免费密集回归的不确定性估计，一个未被认识到的重要问题，并提供了一个理论建设证明这样的估计。我们提出了三种简单且可扩展的方法来分析训练网络在可容忍扰动下的输出方差：推断转换，推断噪声和推断辍学。它们只在推理过程中运行，而不需要重新训练、重新设计或微调模型，而这通常是最先进的不确定性估计方法所要求的。令人惊讶的是，即使在训练中不涉及这种扰动，与需要训练的最先进的方法相比，我们的方法也能产生相当甚至更好的不确定性估计。代码可在https://github.com/lumi9587/train-free-uncertainty上获得。
Uncertainty estimation is an essential step in the evaluation of the robustness for deep learning models in computer vision, especially when applied in risk-sensitive areas. However, most state-of-the-art deep learning models either fail to obtain uncertainty estimation or need significant modification (e.g., formulating a proper Bayesian treatment) to obtain it. Most previous methods are not able to take an arbitrary model off the shelf and generate uncertainty estimation without retraining or redesigning it. To address this gap, we perform a systematic exploration into training-free uncertainty estimation for dense regression, an unrecognized yet important problem, and provide a theoretical construction justifying such estimations. We propose three simple and scalable methods to analyze the variance of outputs from a trained network under tolerable perturbations: infer-transformation, infer-noise, and infer-dropout. They operate solely during the inference, without the need to re-train, re-design, or fine-tune the models, as typically required by state-of-the-art uncertainty estimation methods. Surprisingly, even without involving such perturbations in training, our methods produce comparable or even better uncertainty estimation when compared to training-required state-of-the-art methods. Code is available at https://github.com/lumi9587/train-free-uncertainty.