Deep neural networks have enabled major progresses in semantic segmentation. However, even the most advanced neural architectures suffer from important limitations. First, they are vulnerable to catastrophic forgetting, i.e. they perform poorly when they are required to incrementally update their model as new classes are available. Second, they rely on large amount of pixel-level annotations to produce accurate segmentation maps. To tackle these issues, we introduce a novel incremental class learning approach for semantic segmentation taking into account a peculiar aspect of this task: since each training step provides annotation only for a subset of all possible classes, pixels of the background class exhibit a semantic shift. Therefore, we revisit the traditional distillation paradigm by designing novel loss terms which explicitly account for the background shift. Additionally, we introduce a novel strategy to initialize classifier's parameters at each step in order to prevent biased predictions toward the background class. Finally, we demonstrate that our approach can be extended to point- and scribble-based weakly supervised segmentation, modeling the partial annotations to create priors for unlabeled pixels. We demonstrate the effectiveness of our approach with an extensive evaluation on the Pascal-VOC, ADE20K, and Cityscapes datasets, significantly outperforming state-of-the-art methods.
翻译:深心神经网络在语义分割方面取得了重大进步。 但是, 即使最先进的神经结构也存在重要的限制。 首先, 它们很容易被灾难性的遗忘, 也就是说, 当需要它们随着新等级的出现而逐步更新模型时, 它们表现不佳。 其次, 它们依赖大量的像素级说明来制作准确的分解图。 为了解决这些问题, 我们引入了一种新的语义分解递增班学习方法, 以考虑到这项任务的一个特殊方面: 因为每个培训步骤都只为所有可能的班级的子组提供说明, 背景类的像素表现出一种语义变化。 因此, 我们重新审视传统的蒸馏模式, 设计新的损失术语来明确解释背景变化。 此外, 我们引入了一个新的战略, 初始化分类员参数, 以防止对背景类有偏差的预测。 最后, 我们证明我们的方法可以扩展为基于点和尖锐的、 粗略的分解分解分解分解, 建模部分说明为创建未标的平面平面的平面、 20 的市, 我们展示了我们广泛评估方法。 我们展示了我们快速的州- 数据-, 我们展示了我们城市- 的州级- 的州- 展示了我们的数据- 方法。