Many top-down architectures for instance segmentation achieve significant success when trained and tested on pre-defined closed-world taxonomy. However, when deployed in the open world, they exhibit notable bias towards seen classes and suffer from significant performance drop. In this work, we propose a novel approach for open world instance segmentation called bottom-Up and top-Down Open-world Segmentation (UDOS) that combines classical bottom-up segmentation algorithms within a top-down learning framework. UDOS first predicts parts of objects using a top-down network trained with weak supervision from bottom-up segmentations. The bottom-up segmentations are class-agnostic and do not overfit to specific taxonomies. The part-masks are then fed into affinity-based grouping and refinement modules to predict robust instance-level segmentations. UDOS enjoys both the speed and efficiency from the top-down architectures and the generalization ability to unseen categories from bottom-up supervision. We validate the strengths of UDOS on multiple cross-category as well as cross-dataset transfer tasks from 5 challenging datasets including MS-COCO, LVIS, ADE20k, UVO and OpenImages, achieving significant improvements over state-of-the-art across the board. Our code and models are available on our project page.
翻译:许多自上而下结构,例如,分层结构,在经过预先界定的封闭世界分类学的培训和测试后,取得了显著的成功。然而,当在开放世界中部署时,它们表现出显著的偏向,偏向可见的分类,并遭受显著的绩效下降。在这项工作中,我们提出了一种新颖的开放世界分化方法,称为“自下而上”和“自上而下自上而下开放世界分层(UDOS)”,将传统的自下而上分层算法与自上而下自上而下学习框架内的经典分层算法结合起来。UDOS首先利用一个自上而下网络预测物体的部分,该自上而下网络经过自下、自下而上、自下而上、自上而上、自上而上、自上而上、自上而上而上、自上而上、自上而上而上、自上而上而上而上、自上而上而上、自上而上而上、自上而上而上、自上而上而上而上、自上而上之五具有挑战性的数据转换任务转移任务,包括MS-CO、LSVI和UAIS在我们的O-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-com-com-com-com-com-com-com-com-com-com-com-com-com-com-c-com-com-com-com-com-com-com-com-com-com-com-com-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-to-s-s-s-s-to-to-to-to-to-to-to-to-to-to-to-to-to-to-s-</s>