CANDY: Category-Kernelized Dynamic Convolution for Instance Segmentation

Abstract

Instance segmentation has been dominated by the paradigm that predicts masks using local RoI features and simplicity frameworks based on global mask prediction. Despite the comparable performance between local-based and global-based approaches, the AP results of objects on different scales vary significantly. In this paper, we first point out that the key factor to bridging such a gap lies in the utilization of local RoI information for global mask prediction. Then, we observe a ’class-agnostic segmentation’ problem exists in the nearby region of interesting objects after implementing the above combination. To overcome this issue, we further propose a CAtegory-kerNelized DYnamic (CANDY) convolution. Benefiting from it, the discriminative ability of the resulting instance segmentation framework, i.e., CANDY-Mask, on foreground objects is significantly enhanced. Extensive experiments on the MS-COCO dataset are conducted to verify the performance of CANDY-Mask. Our proposed CANDY-Mask obtains 48.1% boxes AP and 40.7% masks AP on the MS-COCO test-dev set with ResNet50 backbone, achieving state-of-the-art among various models.