Object Detection Free Instance Segmentation With Labeling Transformations
arXiv:1611.08991
Abstract
Instance segmentation has attracted recent attention in computer vision and existing methods in this domain mostly have an object detection stage. In this paper, we study the intrinsic challenge of the instance segmentation problem, the presence of a quotient space (swapping the labels of different instances leads to the same result), and propose new methods that are object proposal- and object detection- free. We propose three alternative methods, namely pixel-based affinity mapping, superpixel-based affinity learning, and boundary-based component segmentation, all focusing on performing labeling transformations to cope with the quotient space problem. By adopting fully convolutional neural networks (FCN) like models, our framework attains competitive results on both the PASCAL dataset (object-centric) and the Gland dataset (texture-centric), which the existing methods are not able to do. Our work also has the advantages in its transparency, simplicity, and being all segmentation based.
10 pages, 5 figures
References in corpus (12)
- Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
- Multi-Scale Context Aggregation by Dilated Convolutions
- Fully Convolutional Networks for Semantic Segmentation
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
- Rich feature hierarchies for accurate object detection and semantic segmentation
- Gland Instance Segmentation Using Deep Multichannel Neural Networks
- Proposal-free Network for Instance-level Object Segmentation
- Analyzing the Performance of Multilayer Neural Networks for Object Recognition
- Instance-sensitive Fully Convolutional Networks
- Instance-Level Segmentation for Autonomous Driving with Deep Densely Connected MRFs
- Iterative Instance Segmentation
- Reversible Recursive Instance-level Object Segmentation