Explicit Shape Encoding for Real-Time Instance Segmentation
This work addresses the computational bottleneck in real-time instance segmentation for applications requiring fast processing, such as autonomous driving or video analysis, though it is incremental as it builds on existing object detectors.
The paper tackles the problem of high computational cost in instance segmentation by proposing ESE-Seg, a top-down framework that uses explicit shape encoding to decode object shapes efficiently, achieving instance segmentation at speeds comparable to object detection. It reports that ESE-Seg with YOLOv3 outperforms Mask R-CNN on Pascal VOC 2012 at mAP^r@0.5 while being 7 times faster.
In this paper, we propose a novel top-down instance segmentation framework based on explicit shape encoding, named \textbf{ESE-Seg}. It largely reduces the computational consumption of the instance segmentation by explicitly decoding the multiple object shapes with tensor operations, thus performs the instance segmentation at almost the same speed as the object detection. ESE-Seg is based on a novel shape signature Inner-center Radius (IR), Chebyshev polynomial fitting and the strong modern object detectors. ESE-Seg with YOLOv3 outperforms the Mask R-CNN on Pascal VOC 2012 at mAP$^r$@0.5 while 7 times faster.