paper-with-me

Papers

PSNet: Parallel Symmetric Network for Video Salient Object Detection

2022-10-12 · Runmin Cong, Weiyu Song, Jianjun Lei, Guanghui Yue, Yao Zhao, Sam Kwong

For the video salient object detection (VSOD) task, how to excavate the information from the appearance modality and the motion modality has always been a topic of great concern. The two-stream structure, including an RGB appearance stream and an optical flow motion stream, has been widely used as a typical pipeline for VSOD tasks, but the existing methods usually only use motion features to unidirectionally guide appearance features or adaptively but blindly fuse two modality features. However, these methods underperform in diverse scenarios due to the uncomprehensive and unspecific learning schemes. In this paper, following a more secure modeling philosophy, we deeply investigate the importance of appearance modality and motion modality in a more comprehensive way and propose a VSOD network with up and down parallel symmetry, named PSNet. Two parallel branches with different dominant modalities are set to achieve complete video saliency decoding with the cooperation of the Gather Diffusion Reinforcement (GDR) module and Cross-modality Refinement and Complement (CRC) module. Finally, we use the Importance Perception Fusion (IPF) module to fuse the features from two parallel branches according to their different importance in different scenarios. Experiments on four dataset benchmarks demonstrate that our method achieves desirable and competitive performance.

📄 PDF Abstract BibTeX arXiv:2210.05912

Code (0)

등록된 구현이 없습니다.

Tasks

Objectobject-detectionObject DetectionOptical Flow EstimationPhilosophySalient Object DetectionVideo Salient Object Detection

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Parallel Capsule Networks for Classification of White Blood Cells

2021-08-05 · Juan P. Vigueras-Guillén, Arijit Patra, Ola Engkvist, Frank Seeliger

Capsule Networks (CapsNets) is a machine learning architecture proposed to overcome some of the shortcomings of convolutional neural networks (CNNs). However, CapsNets have mainly outperformed CNNs in datasets where imag…

Classification

Self-Attention Capsule Networks for Object Classification

2019-04-29 · Assaf Hoogi, Brian Wilcox, Yachee Gupta, Daniel L. Rubin

We propose a novel architecture for object classification, called Self-Attention Capsule Networks (SACN). SACN is the first model that incorporates the Self-Attention mechanism as an integral layer within the Capsule Net…

ClassificationGeneral ClassificationImage ClassificationObject

PDR-CapsNet: an Energy-Efficient Parallel Approach to Dynamic Routing in Capsule Networks

2023-10-04 · Samaneh Javadinia, Amirali Baniasadi

Convolutional Neural Networks (CNNs) have produced state-of-the-art results for image classification tasks. However, they are limited in their ability to handle rotational and viewpoint variations due to information loss…

GPUimage-classificationImage Classification

Employing Deep Part-Object Relationships for Salient Object Detection

2019-10-01 · ICCV 2019 10 · Yi Liu, Qiang Zhang, Dingwen Zhang, Jungong Han

Despite Convolutional Neural Networks (CNNs) based methods have been successful in detecting salient objects, their underlying mechanism that decides the salient intensity of each image part separately cannot avoid incon…

Objectobject-detectionObject DetectionRGB Salient Object Detection+1

Enabling Highly Efficient Capsule Networks Processing Through A PIM-Based Architecture Design

2019-11-07 · Xingyao Zhang, Shuaiwen Leon Song, Chenhao Xie, Jing Wang 외

In recent years, the CNNs have achieved great successes in the image processing tasks, e.g., image recognition and object detection. Unfortunately, traditional CNN's classification is found to be easily misled by increas…

GPUImage Segmentationobject-detectionObject Detection+1