Proposal-free Network for Instance-level Object Segmentation

Abstract

Instance-level object segmentation is an important yet under-explored task. The few existing studies are almost all based on region proposal methods to extract candidate segments and then utilize object classification to produce final results. Nonetheless, generating accurate region proposals itself is quite challenging. In this work, we propose a Proposal-Free Network (PFN ) to address the instance-level object segmentation problem, which outputs the instance numbers of different categories and the pixel-level information on 1) the coordinates of the instance bounding box each pixel belongs to, and 2) the confidences of different categories for each pixel, based on pixel-to-pixel deep convolutional neural network. All the outputs together, by using any off-the-shelf clustering method for simple post-processing, can naturally generate the ultimate instance-level object segmentation results. The whole PFN can be easily trained in an end-to-end way without the requirement of a proposal generation stage. Extensive evaluations on the challenging PASCAL VOC 2012 semantic segmentation benchmark demonstrate that the proposed PFN solution well beats the state-of-the-arts for instance-level object segmentation. In particular, the $A{P}^r$ over 20 classes at 0.5 IoU reaches 58.7% by PFN, significantly higher than 43.8% and 46.3% by the state-of-the-art algorithms, SDS [9] and [16], respectively.

14 pages

References in corpus (7)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Fully Convolutional Networks for Semantic Segmentation
• Learning to Segment Object Candidates
• Learning Deconvolution Network for Semantic Segmentation
• Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
• Simultaneous Detection and Segmentation
• Computational Baby Learning

Cited by in corpus (44)

• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
• Semantic Instance Segmentation with a Discriminative Loss Function
• Evolution of Image Segmentation using Deep Convolutional Neural Network: A Survey
• Semantic Instance Segmentation via Deep Metric Learning
• DeeperLab: Single-Shot Image Parser
• Bridging Category-level and Instance-level Semantic Image Segmentation
• ConnNet: A Long-Range Relation-Aware Pixel-Connectivity Network for Salient Segmentation
• Recurrent Neural Networks for Semantic Instance Segmentation
• Multiple-Human Parsing in the Wild
• Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing
• Deep Watershed Transform for Instance Segmentation
• MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features
• SSAP: Single-Shot Instance Segmentation With Affinity Pyramid
• Instance-level Human Parsing via Part Grouping Network
• Attention-guided Unified Network for Panoptic Segmentation
• InstanceCut: from Edges to Instances with MultiCut
• Holistic, Instance-Level Human Parsing
• Instance-Level Segmentation for Autonomous Driving with Deep Densely Connected MRFs
• Effective Use of Dilated Convolutions for Segmenting Small Object Instances in Remote Sensing Imagery
• Learning to decompose for object detection and instance segmentation
• Object Detection Free Instance Segmentation With Labeling Transformations
• Joint Graph Decomposition and Node Labeling: Problem, Algorithms, Applications
• Zoom Better to See Clearer: Human and Object Parsing with Hierarchical Auto-Zoom Net
• Instance Segmentation with Point Supervision
• Learning Deep Representations for Semantic Image Parsing: a Comprehensive Overview
• Pose2Instance: Harnessing Keypoints for Person Instance Segmentation
• Reversible Recursive Instance-level Object Segmentation
• Learning Instance Occlusion for Panoptic Segmentation
• Boundary-aware Instance Segmentation
• SketchParse : Towards Rich Descriptions for Poorly Drawn Sketches using Multi-Task Hierarchical Deep Networks
• Semi-convolutional Operators for Instance Segmentation
• Multi-person Articulated Tracking with Spatial and Temporal Embeddings
• LUCSS: Language-based User-customized Colourization of Scene Sketches
• Pixelwise Instance Segmentation with a Dynamically Instantiated Network
• Weakly- and Semi-Supervised Panoptic Segmentation
• Adaptive Temporal Encoding Network for Video Instance-level Human Parsing
• A Fully Convolutional Tri-branch Network (FCTN) for Domain Adaptation
• Distance to Center of Mass Encoding for Instance Segmentation
• Semantic Segmentation and Object Detection Towards Instance Segmentation: Breast Tumor Identification
• MaskPlus: Improving Mask Generation for Instance Segmentation
• Affinity Derivation and Graph Merge for Instance Segmentation
• Bounding Box Embedding for Single Shot Person Instance Segmentation
• A Holistic Approach for Data-Driven Object Cutout