A Novel Video Salient Object Detection Method via Semi-supervised Motion Quality Perception

by   Chenglizhao Chen, et al.

Previous video salient object detection (VSOD) approaches have mainly focused on designing fancy networks to achieve their performance improvements. However, with the slow-down in development of deep learning techniques recently, it may become more and more difficult to anticipate another breakthrough via fancy networks solely. To this end, this paper proposes a universal learning scheme to get a further 3% performance improvement for all state-of-the-art (SOTA) methods. The major highlight of our method is that we resort the "motion quality"—a brand new concept, to select a sub-group of video frames from the original testing set to construct a new training set. The selected frames in this new training set should all contain high-quality motions, in which the salient objects will have large probability to be successfully detected by the "target SOTA method"—the one we want to improve. Consequently, we can achieve a significant performance improvement by using this new training set to start a new round of network training. During this new round training, the VSOD results of the target SOTA method will be applied as the pseudo training objectives. Our novel learning scheme is simple yet effective, and its semi-supervised methodology may have large potential to inspire the VSOD community in the future.


page 1

page 2

page 4

page 5

page 6

page 9


Semi-Supervised Video Salient Object Detection Using Pseudo-Labels

Deep learning-based video salient object detection has recently achieved...

A Deeper Look at Salient Object Detection: Bi-stream Network with a Small Training Dataset

Compared with the conventional hand-crafted approaches, the deep learnin...

Weakly Supervised Video Salient Object Detection

Significant performance improvement has been achieved for fully-supervis...

SSVOD: Semi-Supervised Video Object Detection with Sparse Annotations

Despite significant progress in semi-supervised learning for image objec...

Semi-Supervised Cross-Modal Salient Object Detection with U-Structure Networks

Salient Object Detection (SOD) is a popular and important topic aimed at...

Label, Verify, Correct: A Simple Few Shot Object Detection Method

The objective of this paper is few-shot object detection (FSOD) – the ta...

Semantic Motion Correction Via Iterative Nonlinear Optimization and Animation

Here, we present an end-to-end method to create 2D animation for a goalk...

Please sign up or login with your details

Forgot password? Click here to reset