F2Net: Learning to Focus on the Foreground for Unsupervised Video Object Segmentation

by   Daizong Liu, et al.

Although deep learning based methods have achieved great progress in unsupervised video object segmentation, difficult scenarios (e.g., visual similarity, occlusions, and appearance changing) are still not well-handled. To alleviate these issues, we propose a novel Focus on Foreground Network (F2Net), which delves into the intra-inter frame details for the foreground objects and thus effectively improve the segmentation performance. Specifically, our proposed network consists of three main parts: Siamese Encoder Module, Center Guiding Appearance Diffusion Module, and Dynamic Information Fusion Module. Firstly, we take a siamese encoder to extract the feature representations of paired frames (reference frame and current frame). Then, a Center Guiding Appearance Diffusion Module is designed to capture the inter-frame feature (dense correspondences between reference frame and current frame), intra-frame feature (dense correspondences in current frame), and original semantic feature of current frame. Specifically, we establish a Center Prediction Branch to predict the center location of the foreground object in current frame and leverage the center point information as spatial guidance prior to enhance the inter-frame and intra-frame feature extraction, and thus the feature representation considerably focus on the foreground objects. Finally, we propose a Dynamic Information Fusion Module to automatically select relatively important features through three aforementioned different level features. Extensive experiments on DAVIS2016, Youtube-object, and FBMS datasets show that our proposed F2Net achieves the state-of-the-art performance with significant improvement.


page 1

page 3

page 7


Implicit Motion-Compensated Network for Unsupervised Video Object Segmentation

Unsupervised video object segmentation (UVOS) aims at automatically sepa...

Learning Shape Priors by Pairwise Comparison for Robust Semantic Segmentation

Semantic segmentation is important in medical image analysis. Inspired b...

Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes

Current efficient LiDAR-based detection frameworks are lacking in exploi...

Unsupervised segmentation via semantic-apparent feature fusion

Foreground segmentation is an essential task in the field of image under...

See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks

We introduce a novel network, called CO-attention Siamese Network (COSNe...

Foreground Guidance and Multi-Layer Feature Fusion for Unsupervised Object Discovery with Transformers

Unsupervised object discovery (UOD) has recently shown encouraging progr...

Learning Inter- and Intra-frame Representations for Non-Lambertian Photometric Stereo

In this paper, we build a two-stage Convolutional Neural Network (CNN) a...

Please sign up or login with your details

Forgot password? Click here to reset