U2-ONet: A Two-level Nested Octave U-structure with Multiscale Attention Mechanism for Moving Instances Segmentation
arXiv:2007.13092
Abstract
Most scenes in practical applications are dynamic scenes containing moving objects, so segmenting accurately moving objects is crucial for many computer vision applications. In order to efficiently segment out all moving objects in the scene, regardless of whether the object has a predefined semantic label, we propose a two-level nested Octave U-structure network with a multiscale attention mechanism called U2-ONet. Each stage of U2-ONet is filled with our newly designed Octave ReSidual U-block (ORSU) to enhance the ability to obtain more context information at different scales while reducing spatial redundancy of feature maps. In order to efficiently train our multi-scale deep network, we introduce a hierarchical training supervision strategy that calculates the loss at each level while adding a knowledge matching loss to keep the optimization consistency. Experimental results show that our method achieves state-of-the-art performance in several general moving objects segmentation datasets.
10 pages, 7 figures,
References in corpus (9)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- YOLOv3: An Incremental Improvement
- U-Net: Going Deeper with Nested U-Structure for Salient Object Detection
- YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark
- Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
- 3D Rigid Motion Segmentation with Mixed and Unknown Number of Models
- Anchor Diffusion for Unsupervised Video Object Segmentation
- Collaborative Video Object Segmentation by Foreground-Background Integration
- A Detailed Rubric for Motion Segmentation