Publication Type

Journal Article

Version

acceptedVersion

Publication Date

8-2024

Abstract

The fully convolutional network (FCN) has dominated salient object detection for a long period. However, the locality of CNN requires the model deep enough to have a global receptive field and such a deep model always leads to the loss of local details. In this paper, we introduce a new attention-based encoder, vision transformer, into salient object detection to ensure the globalization of the representations from shallow to deep layers. With the global view in very shallow layers, the transformer encoder preserves more local representations to recover the spatial details in final saliency maps. Besides, as each layer can capture a global view of its previous layer, adjacent layers can implicitly maximize the representation differences and minimize the redundant features, making every output feature of transformer layers contribute uniquely to the final prediction. To decode features from the transformer, we propose a simple yet effective deeply-transformed decoder. The decoder densely decodes and upsamples the transformer features, generating the final saliency map with less noise injection. Experimental results demonstrate that our method significantly outperforms other FCN-based and transformer-based methods in five benchmarks by a large margin, with an average of 12.17% improvement in terms of Mean Absolute Error (MAE).

Keywords

Transformer, salient object detection

Discipline

Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

IEEE Transactions on Emerging Topics in Computational Intelligence

Volume

8

Issue

4

First Page

2870

Last Page

2879

ISSN

2471-285X

Identifier

10.1109/TETCI.2024.3380442

Publisher

Institute of Electrical and Electronics Engineers

Additional URL

https://doi.org/10.1109/TETCI.2024.3380442

Download

Share

COinS