论文标题
可区分的TOP-K分类学习
Differentiable Top-k Classification Learning
论文作者
论文摘要
TOP-K分类精度是机器学习中的核心指标之一。在这里，K是通常的积极整数，例如1或5，导致了前1名或前5个训练目标。在这项工作中，我们放宽了此假设并同时优化多个k的模型，而不是使用单个k。利用最新的分类和排名方面的进步，我们提出了可区分的TOP-K跨膜分类损失。这允许培训网络，同时不仅考虑了TOP-1预测，还可以考虑TOP-2和TOP-5预测。我们评估了针对最先进架构的微调以及从头开始培训的损失功能。我们发现，放松K不仅会产生更好的前5个精度，还可以提高前1个精度。当微调公开可用的成像网模型时，我们为这些模型实现了新的最新技术。
The top-k classification accuracy is one of the core metrics in machine learning. Here, k is conventionally a positive integer, such as 1 or 5, leading to top-1 or top-5 training objectives. In this work, we relax this assumption and optimize the model for multiple k simultaneously instead of using a single k. Leveraging recent advances in differentiable sorting and ranking, we propose a differentiable top-k cross-entropy classification loss. This allows training the network while not only considering the top-1 prediction, but also, e.g., the top-2 and top-5 predictions. We evaluate the proposed loss function for fine-tuning on state-of-the-art architectures, as well as for training from scratch. We find that relaxing k does not only produce better top-5 accuracies, but also leads to top-1 accuracy improvements. When fine-tuning publicly available ImageNet models, we achieve a new state-of-the-art for these models.
