论文标题
深入到变压器进行增量语义细分
Delving into Transformer for Incremental Semantic Segmentation
论文作者
论文摘要
增量语义细分（ISS）是一个新的任务，其中通过添加新类来更新旧模型。目前，基于卷积神经网络的方法在ISS中占主导地位。但是，研究表明，这种方法在学习新任务的同时保持良好的旧绩效（灾难性遗忘）很难学习新任务。相反，基于变压器的方法具有自然的优势，可以遏制灾难性遗忘，因为它可以对长期和短期任务进行建模。在这项工作中，我们探讨了基于变压器的架构更适合ISS的原因，因此提出了提出的Tiss，这是一种基于变压器的逐步语义分割的方法。此外，为了更好地减轻ISS的可转移性，我们可以分别模仿类似的特征并增强特征多样性，从而更好地减轻灾难性的遗忘，这可以进一步改善组织的性能。在使用Pascal-VOC 2012和ADE20K数据集的广泛实验设置下，我们的方法显着优于最先进的递增语义分割方法。
Incremental semantic segmentation(ISS) is an emerging task where old model is updated by incrementally adding new classes. At present, methods based on convolutional neural networks are dominant in ISS. However, studies have shown that such methods have difficulty in learning new tasks while maintaining good performance on old ones (catastrophic forgetting). In contrast, a Transformer based method has a natural advantage in curbing catastrophic forgetting due to its ability to model both long-term and short-term tasks. In this work, we explore the reasons why Transformer based architecture are more suitable for ISS, and accordingly propose propose TISS, a Transformer based method for Incremental Semantic Segmentation. In addition, to better alleviate catastrophic forgetting while preserving transferability on ISS, we introduce two patch-wise contrastive losses to imitate similar features and enhance feature diversity respectively, which can further improve the performance of TISS. Under extensive experimental settings with Pascal-VOC 2012 and ADE20K datasets, our method significantly outperforms state-of-the-art incremental semantic segmentation methods.
