Reversible Recursive Instance-level Object Segmentation

Abstract

In this work, we propose a novel Reversible Recursive Instance-level Object Segmentation (R2-IOS) framework to address the challenging instance-level object segmentation task. R2-IOS consists of a reversible proposal refinement sub-network that predicts bounding box offsets for refining the object proposal locations, and an instance-level segmentation sub-network that generates the foreground mask of the dominant object instance in each proposal. By being recursive, R2-IOS iteratively optimizes the two sub-networks during joint training, in which the refined object proposals and improved segmentation predictions are alternately fed into each other to progressively increase the network capabilities. By being reversible, the proposal refinement sub-network adaptively determines an optimal number of refinement iterations required for each proposal during both training and testing. Furthermore, to handle multiple overlapped instances within a proposal, an instance-aware denoising autoencoder is introduced into the segmentation sub-network to distinguish the dominant object from other distracting instances. Extensive experiments on the challenging PASCAL VOC 2012 benchmark well demonstrate the superiority of R2-IOS over other state-of-the-art methods. In particular, the ${\text{AP}}^r$ over $20$ classes at $0.5$ IoU achieves $66.7\%$, which significantly outperforms the results of $58.7\%$ by PFN~\cite{PFN} and $46.3\%$ by~\cite{liu2015multi}.

9 pages

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• On the difficulty of training Recurrent Neural Networks
• Going Deeper with Convolutions
• Recurrent Models of Visual Attention
• Fully Convolutional Networks for Semantic Segmentation
• Semantic Image Segmentation via Deep Parsing Network
• BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

Cited by in corpus (7)

• Semantic Instance Segmentation via Deep Metric Learning
• Deep Watershed Transform for Instance Segmentation
• Instance-level Human Parsing via Part Grouping Network
• InstanceCut: from Edges to Instances with MultiCut
• Object Detection Free Instance Segmentation With Labeling Transformations
• Pose2Instance: Harnessing Keypoints for Person Instance Segmentation
• A Holistic Approach for Data-Driven Object Cutout