Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

8-2020

Abstract

In this paper, we propose a simple yet effective approach, named Triple Excitation Network, to reinforce the training of video salient object detection (VSOD) from three aspects, spatial, temporal, and online excitations. These excitation mechanisms are designed following the spirit of curriculum learning and aim to reduce learning ambiguities at the beginning of training by selectively exciting feature activations using ground truth. Then we gradually reduce the weight of ground truth excitations by a curriculum rate and replace it by a curriculum complementary map for better and faster convergence. In particular, the spatial excitation strengthens feature activations for clear object boundaries, while the temporal excitation imposes motions to emphasize spatio-temporal salient regions. Spatial and temporal excitations can combat the saliency shifting problem and conflict between spatial and temporal features of VSOD. Furthermore, our semi-curriculum learning design enables the first online refinement strategy for VSOD, which allows exciting and boosting saliency responses during testing without re-training. The proposed triple excitations can easily plug in different VSOD methods. Extensive experiments show the effectiveness of all three excitation methods and the proposed method outperforms state-of-the-art image and video salient object detection methods.

Discipline

Graphics and Human Computer Interfaces | OS and Networks

Research Areas

Information Systems and Management

Publication

Proceedings of the 16th European Conference on Computer Vision (ECCV), Glasgow, United Kingdom, 2020 August 23-28

First Page

212

Last Page

228

ISBN

9783030585570

Identifier

10.1007/978-3-030-58558-7_13

Publisher

Springer - Verlag

City or Country

Berlin, Heidelberg

Additional URL

https://doi.org/10.1007/978-3-030-58558-7_13

Download

Share

COinS