Abstract: Instance segmentation has witnessed a remarkable progress on class-balanced benchmarks. However, they fail to perform as accurately in real-world scenarios, where the category distribution ...
Abstract: Label distribution learning (LDL) is a novel learning paradigm that assigns each instance with a label distribution. Although many specialized LDL algorithms have been proposed, few of them ...
A simple query-based model for fast instance segmentation. State-of-the-art real-time performance under the same setting. Support major segmentation datasets: COCO ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results