Paper Info
Title
Implicit Feature Refinement for Instance Segmentation
Abstract
ABSTRACTWe propose a novel implicit feature refinement module for high-quality instance segmentation. Existing image/video instance segmentation methods rely on explicitly stacked convolutions to refine instance features before the final prediction. In this paper, we first give an empirical comparison of different refinement strategies, which reveals that the widely-used four consecutive convolutions are not necessary. As an alternative, weight-sharing convolution blocks provides competitive performance. When such block is iterated for infinite times, the block output will eventually converge to an equilibrium state. Based on this observation, the implicit feature refinement (IFR) is developed by constructing an implicit function. The equilibrium state of instance features can be obtained by fixed-point iteration via a simulated infinite-depth network. Our IFR enjoys several advantages: 1) simulates an infinite-depth refinement network while only requiring parameters of single residual block; 2) produces high-level equilibrium instance features of global receptive field; 3) serves as a plug-and-play general module easily extended to most object recognition frameworks. Experiments on the COCO and YouTube-VIS benchmarks show that our IFR achieves improved performance on state-of-the-art image/video instance segmentation frameworks, while reducing the parameter burden (e.g. 1% AP improvement on Mask R-CNN with only 30.0% parameters in mask head). Code will be made available at \hrefhttps://github.com/lufanma/IFR.git https://github.com/lufanma/IFR.git .
Year
DOI
Venue
2021
10.1145/3474085.3475449
International Multimedia Conference
DocType
Citations 
PageRank 
Conference
0
0.34
References 
Authors
0
6
Name
Order
Citations
PageRank
Lufan Ma100.34
Tiancai Wang200.34
Bin Dong300.68
Yan Jiangpeng414.75
Xiu Li502.70
Xiangyu Zhang613044437.66