Long-tailed instance segmentation is a challenging task due to the extreme imbalance of training samples among classes. It causes severe biases of the head classes (with majority samples) against the tailed ones. This renders "how to appropriately define and alleviate the bias" one of the most important issues. Prior works mainly use label distribution or mean score information to indicate a coarse-grained bias. In this paper, we explore to excavate the confusion matrix, which carries the fine-grained misclassification details, to relieve the pairwise biases, generalizing the coarse one. To this end, we propose a novel Pairwise Class Balance (PCB) method, built upon a confusion matrix which is updated during training to accumulate the ongoing prediction preferences. PCB generates fightback soft labels for regularization during training. Besides, an iterative learning paradigm is developed to support a progressive and smooth regularization in such debiasing. PCB can be plugged and played to any existing method as a complement. Experimental results on LVIS demonstrate that our method achieves state-of-the-art performance without bells and whistles. Superior results across various architectures show the generalization ability.

翻译：长尾分类是一个艰巨的任务, 原因是各班培训样本极不平衡。 它给头类( 多数样本) 对尾部的样本造成严重的偏差。 这使得“ 如何适当定义和减轻偏差” 成为最重要的问题之一。 先前的工作主要是使用标签分布或平均评分信息来表明粗略的偏差。 本文中, 我们探索如何挖掘包含细微的分类错误细节的混乱矩阵, 以缓解对称偏差, 概括粗略的偏差。 为此, 我们建议了一个新的“ 彩虹类平衡( PCB) ” 方法, 其建立于在培训期间更新的混乱矩阵, 以积累持续的预测偏好。 多氯联苯在培训期间生成回击软标签, 以便在常规化过程中进行回击。 此外, 正在开发一个互动学习模式, 以支持这种偏差的渐进和平稳的调节。 多氯联苯可以被塞住, 并用来补充任何现有的方法。 LVIS 实验结果显示, 我们的方法在没有钟和哨子的情况下实现了状态性的表现。 跨结构的优异的结果显示一般的能力 。