Explicit Shape Encoding for Real-Time Instance Segmentation

ICCV 2019 Wenqiang XuHaiyang WangFubo QiCewu 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... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Semantic Contour Prediction Sbd val ESE-50 AP50 39.1 # 3
AP70 10.5 # 3
APvol 32.6 # 3
Semantic Contour Prediction Sbd val ESE-20 AP50 40.7 # 2
AP70 12.1 # 2
APvol 35.3 # 2

Methods used in the Paper