论文标题
使用Gumbel优化损失的长尾实例分割
Long-tailed Instance Segmentation using Gumbel Optimized Loss
论文作者
论文摘要
最近在对象检测和细分领域取得了重大进步。但是，在罕见类别方面，最新方法无法检测到它们，从而在稀有类别和频繁类别之间存在显着的性能差距。在本文中，我们确定深探测器中使用的Sigmoid或SoftMax功能是低性能的主要原因，并且是长尾检测和分割的优势。为了解决这个问题，我们开发了牙龈优化的损失（GOL），以进行长尾检测和分割。考虑到大多数长尾检测中的大多数类别的预期概率较低的事实，它与不平衡数据集中罕见类别的牙龈分布保持一致。拟议的GOL在AP上显着优于最佳的最新方法，并将整体分割率提高9.0％，并将检测到8.0％，尤其是在LVIS数据集上，对Mask-Rcnn的检测尤其提高了20.3％。代码可用：https：//github.com/kostas1515/gol
Major advancements have been made in the field of object detection and segmentation recently. However, when it comes to rare categories, the state-of-the-art methods fail to detect them, resulting in a significant performance gap between rare and frequent categories. In this paper, we identify that Sigmoid or Softmax functions used in deep detectors are a major reason for low performance and are sub-optimal for long-tailed detection and segmentation. To address this, we develop a Gumbel Optimized Loss (GOL), for long-tailed detection and segmentation. It aligns with the Gumbel distribution of rare classes in imbalanced datasets, considering the fact that most classes in long-tailed detection have low expected probability. The proposed GOL significantly outperforms the best state-of-the-art method by 1.1% on AP , and boosts the overall segmentation by 9.0% and detection by 8.0%, particularly improving detection of rare classes by 20.3%, compared to Mask-RCNN, on LVIS dataset. Code available at: https://github.com/kostas1515/GOL
