Explicit Shape Encoding for Real-Time Instance Segmentation

ICCV 2019  ·  Wenqiang Xu, Haiyang Wang, Fubo Qi, Cewu Lu ·

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.

PDF Abstract ICCV 2019 PDF ICCV 2019 Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Semantic Contour Prediction Sbd val ESE-20 AP50 40.7 # 3
AP70 12.1 # 3
APvol 35.3 # 3
Semantic Contour Prediction Sbd val ESE-50 AP50 39.1 # 4
AP70 10.5 # 4
APvol 32.6 # 4