论文标题
角间隙：通过模型校准降低图像难度的不确定性
Angular Gap: Reducing the Uncertainty of Image Difficulty through Model Calibration
论文作者
论文摘要
课程学习需要示例难以从轻松到硬进行。但是，很少研究图像难度的信誉，这会严重影响课程的有效性。在这项工作中，我们提出了角度差距，这是一个基于特征嵌入和通过超球体学习构建的类别嵌入和类体重嵌入之间的角度差异的难度度量。为了确定难度估计，我们将按类模型校准作为培训后技术引入学习的双曲线空间。这弥合了概率模型校准与超级学习的角度距离估计之间的差距。我们显示了校准的角度差距的优越性，而不是最近在CIFAR10-H和ImagenEtV2上的难度指标。我们进一步提出了基于角度间隙的课程学习，以进行无监督的域适应性，从而可以转化为学习简易样品到采矿硬样品。我们将该课程与最先进的自我训练方法（CST）相结合。拟议的课程CST学习了强大的表示形式，并且在Office31和Visda 2017上的最新基线表现出色。
Curriculum learning needs example difficulty to proceed from easy to hard. However, the credibility of image difficulty is rarely investigated, which can seriously affect the effectiveness of curricula. In this work, we propose Angular Gap, a measure of difficulty based on the difference in angular distance between feature embeddings and class-weight embeddings built by hyperspherical learning. To ascertain difficulty estimation, we introduce class-wise model calibration, as a post-training technique, to the learnt hyperbolic space. This bridges the gap between probabilistic model calibration and angular distance estimation of hyperspherical learning. We show the superiority of our calibrated Angular Gap over recent difficulty metrics on CIFAR10-H and ImageNetV2. We further propose Angular Gap based curriculum learning for unsupervised domain adaptation that can translate from learning easy samples to mining hard samples. We combine this curriculum with a state-of-the-art self-training method, Cycle Self Training (CST). The proposed Curricular CST learns robust representations and outperforms recent baselines on Office31 and VisDA 2017.
