SiamPolar: Semi-supervised Realtime Video Object Segmentation with Polar Representation
Not on the map. Why?
Abstract (arXiv)
Video object segmentation (VOS) is an essential part of autonomous vehicle navigation. The real-time speed is very important for the autonomous vehicle algorithms along with the accuracy metric. In this paper, we propose a semi-supervised real-time method based on the Siamese network using a new polar representation. The input of bounding boxes is initialized rather than the object masks, which are applied to the video object detection tasks. The polar representation could reduce the parameters for encoding masks with subtle accuracy loss so that the algorithm speed can be improved significantly. An asymmetric siamese network is also developed to extract the features from different spatial scales. Moreover, the peeling convolution is proposed to reduce the antagonism among the branches of the polar head. The repeated cross-correlation and semi-FPN are designed based on this idea. The experimental results on the DAVIS-2016 dataset and other public datasets demonstrate the effectiveness of the proposed method.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 27 of its 46 references that are in the map. First posted on arXiv 27 Oct 2021.
Builds on
27 of 46 references.
References · 27
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
- 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
- 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
- 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
- 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 942
- 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 566
- 2018SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networkscited by 445
- 2018Fast Online Object Tracking and Segmentation: A Unifying Approachcited by 272
- 2016One-Shot Video Object Segmentationcited by 233
- 2017Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Networkcited by 208
- 2019PolarMask: Single Shot Instance Segmentation with Polar Representationcited by 188
- 2019FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentationcited by 178
15 more
- 2019Deeper and Wider Siamese Networks for Real-Time Visual Trackingcited by 156
- 2016Learning Video Object Segmentation from Static Imagescited by 151
- 2018Efficient Video Object Segmentation via Network Modulationcited by 98
- 2017Video Object Segmentation Without Temporal Informationcited by 93
- 2017SegFlow: Joint Learning for Video Object Segmentation and Optical Flowcited by 92
- 2020Revisiting the Sibling Head in Object Detectorcited by 82
- 2018Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learningcited by 74
- 2018Fast and Accurate Online Video Object Segmentation via Tracking Partscited by 57
- 2018Video Object Segmentation with Joint Re-identification and Attention-Aware Mask Propagationcited by 56
- 2018Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotationscited by 51
- 2018CNN in MRF: Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRFcited by 48
- 2018MaskRNN: Instance Level Video Object Segmentationcited by 48
- 2016Video Propagation Networkscited by 45
- 2017Pixel-Level Matching for Video Object Segmentation using Convolutional Neural Networkscited by 32
- 2018Video Object Segmentation using Teacher-Student Adaptation in a Human Robot Interaction (HRI) Settingcited by 27
Built on by
Citing papers per year: 2022: 1.
1 paper.