FastMask: Segment Multi-scale Object Candidates in One Shot
This addresses the need for efficient and robust object segmentation across varying scales, with potential applications in real-time vision tasks, though it is incremental as it builds on existing segment proposal networks.
The paper tackles the problem of segmenting multi-scale objects in images by introducing FastMask, a one-shot segment proposal framework that uses hierarchical features in CNNs, achieving 2~5 times faster inference than state-of-the-art methods on MS COCO with improved average recall.
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. Our implementation is available on https://github.com/voidrank/FastMask.