Instance-sensitive Fully Convolutional Networks
arXiv:1603.08678
Abstract
Fully convolutional networks (FCNs) have been proven very successful for semantic segmentation, but the FCN outputs are unaware of object instances. In this paper, we develop FCNs that are capable of proposing instance-level segment candidates. In contrast to the previous FCN that generates one score map, our FCN is designed to compute a small set of instance-sensitive score maps, each of which is the outcome of a pixel-wise classifier of a relative position to instances. On top of these instance-sensitive score maps, a simple assembling module is able to output instance candidate at each position. In contrast to the recent DeepMask method for segmenting instances, our method does not have any high-dimensional layer related to the mask resolution, but instead exploits image local coherence for estimating instances. We present competitive results of instance segment proposal on both PASCAL VOC and MS COCO.
Cited by in corpus (29)
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
- Feature Pyramid Networks for Object Detection
- Semantic Instance Segmentation via Deep Metric Learning
- Gland Instance Segmentation Using Deep Multichannel Neural Networks
- Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection
- Recurrent Neural Networks for Semantic Instance Segmentation
- Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation
- GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud
- MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features
- Instance Segmentation by Deep Coloring
- InstanceCut: from Edges to Instances with MultiCut
- Object Detection Free Instance Segmentation With Labeling Transformations
- ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond
- Learning Deep Representations for Semantic Image Parsing: a Comprehensive Overview
- Pose2Instance: Harnessing Keypoints for Person Instance Segmentation
- PatchPerPix for Instance Segmentation
- Boundary-aware Instance Segmentation
- Video Object Segmentation using Tracked Object Proposals
- Semi-convolutional Operators for Instance Segmentation
- BoundarySqueeze: Image Segmentation as Boundary Squeezing
- Pseudo Mask Augmented Object Detection
- SeGAN: Segmenting and Generating the Invisible
- A Foreground Inference Network for Video Surveillance Using Multi-View Receptive Field
- Instance and Panoptic Segmentation Using Conditional Convolutions
- Pixelwise Instance Segmentation with a Dynamically Instantiated Network
- Instance-Level Salient Object Segmentation
- CASNet: Common Attribute Support Network for image instance and panoptic segmentation
- Object Boundary Guided Semantic Segmentation
- Affinity Derivation and Graph Merge for Instance Segmentation