CycleSegNet: Object Co-segmentation with Cycle Refinement and Region Correspondence
arXiv:2101.01308 · doi:10.1109/TIP.2021.3087401
Abstract
Image co-segmentation is an active computer vision task that aims to segment the common objects from a set of images. Recently, researchers design various learning-based algorithms to undertake the co-segmentation task. The main difficulty in this task is how to effectively transfer information between images to make conditional predictions. In this paper, we present CycleSegNet, a novel framework for the co-segmentation task. Our network design has two key components: a region correspondence module which is the basic operation for exchanging information between local image regions, and a cycle refinement module, which utilizes ConvLSTMs to progressively update image representations and exchange information in a cycle and iterative manner. Extensive experiments demonstrate that our proposed method significantly outperforms the state-of-the-art methods on four popular benchmark datasets -- PASCAL VOC dataset, MSRC dataset, Internet dataset, and iCoseg dataset, by 2.6%, 7.7%, 2.2%, and 2.9%, respectively.
arXiv commentAccept to TIP
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
- Re-thinking Co-Salient Object Detection
- Learning a Discriminative Feature Network for Semantic Segmentation
- Interactive segmentation of medical images through fully convolutional neural networks
- DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning
- Compositional Prototype Network with Multi-view Comparision for Few-Shot Point Cloud Semantic Segmentation
- Show, Match and Segment: Joint Weakly Supervised Learning of Semantic Matching and Object Co-segmentation