Abstract:Few-shot instance segmentation methods are promising when labeled training data for novel classes is scarce. However, current approaches do not facilitate flexible addition of novel classes. They also require that examples of each class are provided at train and test time, which is memory intensive.In this paper, we address these limitations by presenting the first incremental approach to few-shot instance segmentation: iMTFA. We learn discriminative embeddings for object instances that are merged into class representatives.Storing embedding vectors rather than images effectively solves the memory overhead problem. We match these class embeddings at the RoI-level using cosine similarity. This allows us to add new classes without the need for further training or access to previous training data.In a series of experiments, we consistently outperform the current state-of-the-art. Moreover, the reduced memory requirements allow us to evaluate, for the first time, few-shot instance segmentation performance on all classes in COCO jointly .
摘要:在新类标记训练数据较少的情况下,少模块实例分割方法具有广阔的应用前景。但是,目前的方法并不便于灵活地添加新类。他们还要求在训练和测试时间提供每个类的例子,这是内存密集型的。在本文中,我们提出了第一种增量式的少模块实例分割方法:iMTFA,以解决这些局限性。我们学习了合并到类代表中的目标实例的判别嵌入。存储嵌入向量而不是图像有效地解决了内存开销问题。我们使用余弦相似度在roi级别匹配这些类嵌入。这允许我们添加新的类,而不需要进一步的训练或访问以前的训练数据。在一系列的实验中,我们不断超越当前的先进技术。此外,由于内存需求的减少,我们第一次可以联合评估COCO中所有类的少模块实例分割性能。