Multiscale Deep Network with Centerness-Aware Loss for Salient Object Detection
Deep encoder-decoder networks have been adopted for saliency detection and achieved state-of-the-art performance. However, most existing saliency models usually fail to detect very small salient objects. In this paper, we propose a multitask architecture, M2Net, and a novel centerness-aware loss for...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Advances in Multimedia |
| Online Access: | http://dx.doi.org/10.1155/2022/2243927 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Deep encoder-decoder networks have been adopted for saliency detection and achieved state-of-the-art performance. However, most existing saliency models usually fail to detect very small salient objects. In this paper, we propose a multitask architecture, M2Net, and a novel centerness-aware loss for salient object detection. The proposed M2Net aims to solve saliency prediction and centerness prediction simultaneously. Specifically, the network architecture is composed of a bottom-up encoder module, top-down decoder module, and centerness prediction module. In addition, different from binary cross entropy, the proposed centerness-aware loss can guide the proposed M2Net to uniformly highlight the entire salient regions with well-defined object boundaries. Experimental results on five benchmark saliency datasets demonstrate that M2Net outperforms state-of-the-art methods on different evaluation metrics. |
|---|---|
| ISSN: | 1687-5699 |