Deep neural networks have been shown to be highly miscalibrated. often they tend to be overconfident in their predictions. It poses a significant challenge for safety-critical systems to utilise deep neural networks (DNNs), reliably. Many recently proposed approaches to mitigate this have demonstrated substantial progress in improving DNN calibration. However, they hardly touch upon refinement, which historically has been an essential aspect of calibration. Refinement indicates separability of a network's correct and incorrect predictions. This paper presents a theoretically and empirically supported exposition reviewing refinement of a calibrated model. Firstly, we show the breakdown of expected calibration error (ECE), into predicted confidence and refinement under the assumption of over-confident predictions. Secondly, linking with this result, we highlight that regularization based calibration only focuses on naively reducing a model's confidence. This logically has a severe downside to a model's refinement as correct and incorrect predictions become tightly coupled. Lastly, connecting refinement with ECE also provides support to existing refinement based approaches which improve calibration but do not explain the reasoning behind it. We support our claims through rigorous empirical evaluations of many state of the art calibration approaches on widely used datasets and neural networks. We find that many calibration approaches with the likes of label smoothing, mixup etc. lower the usefulness of a DNN by degrading its refinement. Even under natural data shift, this calibration-refinement trade-off holds for the majority of calibration methods.
翻译:深心神经网络被证明高度错误校正。 深心神经网络被证明是高度错误的。 它们往往在预测中过于自信。 它给安全临界系统利用深心神经网络带来重大挑战, 并可靠地利用深心神经网络(DNN)带来重大挑战。 最近提出的许多缓解方法表明,在改进DN校准方面已取得重大进展。 但是,它们几乎没有触及改进,这在历史上一直是校准的一个基本方面。 精炼表明,一个网络正确和不正确的预测具有分离性。 本文介绍了一个理论上和经验上支持的演示,以审查一个校准模型的完善情况。 首先,我们展示了预期校准错误(ECE)的崩溃,在假设过分自信预测的情况下,将它变成预期的信任和完善。 第二,将这一结果联系起来,我们强调,基于校正的规范仅仅侧重于天真地降低模型的信心。 这在逻辑上与模型的改进有严重的下下坡。 最后,与欧洲经委会的改进也支持现有的改进方法,这些改进方法改进了校准,但却没有解释它背后的推理。 我们支持我们主张,通过严格地调整多数贸易网络的调整,我们采用了标准化的校准方法。 采用了很多的校准方法。