FastMask
FastMask: Segment Multi-scale Object Candidates in One Shot
Objects appear to scale differently in natural images. This fact requires methods dealing with object-centric tasks (e.g. object proposal) to have robust performance over variances in object scales. In the paper, we present a novel segment proposal framework, namely FastMask, which takes advantage of hierarchical features in deep convolutional neural networks to segment multi-scale objects in one shot. Innovatively, we adapt segment proposal network into three different functional components (body, neck and head). We further propose a weight-shared residual neck module as well as a scale-tolerant attentional head module for efficient one-shot inference. On MS COCO benchmark, the proposed FastMask outperforms all state-of-the-art segment proposal methods in average recall being 2∼5 times faster. Moreover, with a slight trade-off in accuracy, FastMask can segment objects in near real time (∼13 fps) with 800×600 resolution images, demonstrating its potential in practical applications.
Implementations
FastMask
FastMask: Segment Multi-scale Object Candidates in One Shot
(Published as a spotlight paper at CVPR 2017 in Honolulu, Hawaii)
Hexiang Hu*, Shiyi Lan*, Yuning Jiang, Zhimin Cao, Fei Sha (*Equal contribution. Work was done during their internships at Megvii Inc.)
If you are using code or other related resources from this repository, please cite the following paper