CRVOS: Clue Refining Network for Video Object Segmentation

10 Feb 2020  ·  Suhwan Cho, MyeongAh Cho, Tae-young Chung, Heansung Lee, Sangyoun Lee ·

The encoder-decoder based methods for semi-supervised video object segmentation (Semi-VOS) have received extensive attention due to their superior performances. However, most of them have complex intermediate networks which generate strong specifiers to be robust against challenging scenarios, and this is quite inefficient when dealing with relatively simple scenarios. To solve this problem, we propose a real-time network, Clue Refining Network for Video Object Segmentation (CRVOS), that does not have any intermediate network to efficiently deal with these scenarios. In this work, we propose a simple specifier, referred to as the Clue, which consists of the previous frame's coarse mask and coordinates information. We also propose a novel refine module which shows the better performance compared with the general ones by using a deconvolution layer instead of a bilinear upsampling layer. Our proposed method shows the fastest speed among the existing methods with a competitive accuracy. On DAVIS 2016 validation set, our method achieves 63.5 fps and J&F score of 81.6%.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Semi-Supervised Video Object Segmentation DAVIS 2016 CRVOS Jaccard (Mean) 82.2 # 58
Jaccard (Recall) 93.9 # 16
Jaccard (Decay) 10.0 # 12
F-measure (Mean) 81.0 # 59
F-measure (Recall) 90.3 # 16
F-measure (Decay) 8.8 # 18
J&F 81.6 # 60