The Visual Computer ( IF 3.0 ) Pub Date : 2021-01-20 , DOI: 10.1007/s00371-021-02067-9 Guancheng Chen , Huabiao Qin
Currently, modern object detection algorithms still suffer the imbalance problems especially the foreground–background and foreground–foreground class imbalance. Existing methods generally adopt re-sampling based on the class frequency or re-weighting based on the category prediction probability, such as focal loss, proposed to rebalance the loss assigned to easy negative examples and hard positive examples for single-stage detectors. However, there are still two critical issues unresolved. In practical applications, such as autonomous driving, the class imbalance will become more extreme due to the increased detection field and target distribution characteristics, needing a more effective way to balance the foreground–background class imbalance. Besides, existing methods typically employ the sigmoid or softmax entropy loss for classification task, which we believe is not capable to realize the foreground–foreground class balance. In this paper, we propose a new form of focal loss by re-designing the re-weighting scheme that can calculate the weight according to the probability as well as widen the weight difference of the examples. Besides, we introduce the extended focal loss to multi-class classification task by reformulating the standard softmax cross-entropy loss for better utilizing the discriminant difference of foreground categories, thereby yielding a class-discriminative focal loss. Comprehensive experiments are conducted on the KITTI and BDD dataset, respectively. The results show that our approach can easily surpass focal loss with no more training and inference time cost. Besides, when trained with the proposed loss function, current state-of-the-art object detectors no matter in one-stage or two-stage paradigms can achieve significant performance gains.
中文翻译:
用于自动驾驶的极端不平衡多类别物体检测的类别区分焦点损失
当前,现代物体检测算法仍然遭受不平衡问题,特别是前景-背景和前景-前景类的不平衡。现有的方法通常采用基于类频率的重新采样或基于类别预测概率的加权,例如聚焦损耗,以平衡分配给单级检测器的简单负样本和硬正样本的损失。但是,仍有两个关键问题尚未解决。在诸如自动驾驶之类的实际应用中,由于增加的检测场和目标分布特性,类别失衡将变得更加极端,需要一种更有效的方法来平衡前景-背景类别失衡。此外,现有的方法通常采用S型或softmax熵损失进行分类任务,我们认为这无法实现前台与前台的平衡。在本文中,我们通过重新设计重新加权方案,提出了一种新的焦点损失形式,该方案可以根据概率计算权重并扩大示例的权重差。此外,我们通过重新定义标准softmax交叉熵损失,将扩展的焦点损失引入多类分类任务中,以更好地利用前景类别的判别差异,从而产生分类歧视性焦点损失。分别在KITTI和BDD数据集上进行了综合实验。结果表明,我们的方法可以轻松地克服焦点损失,而无需花费更多的训练和推理时间。此外,在使用建议的损失函数进行训练时,