.png){kind=icon}
.png){kind=icon}
Return
EXTENDED DEEP DOWNSAMPLING NETWORK WITH MULTI-INTERACTIVE REFINEMENT FOR UNDERWATER SALIENT OBJECT DETECTION
.png){kind=icon}
PRE
AI
DOI：10.2316/J.2026.206-1259.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Underwater environment serves as a critical resource for scientific research and marine applications. To suppress noise and generate accurate saliency maps in underwater images, we propose an end-to-end segmentation network. A coarse-to-fine strategy will be adopted which is composed of an extended deep downsampling network and a multi-interactive refinement network. The extended deep downsampling encoder will be employed to obtain more profound features, which may enhance the representation ability of the network. Noise will be suppressed by the self-refinement module and the attention mechanism in each layer. The extended deep features will be fused to form a coarse saliency map. However, this map may be over-segmented during the noise suppression process, resulting in a loss of spatial coherence information. The proposed multi-interactive refinement network is employed to refine the coarse saliency map, aiming to generate an accurate and complete object representation while minimizing noise introduction. Experiments on the underwater datasets and the terrestrial dataset demonstrate that our proposed network achieves accuracy scores of 0.9079, 0.8458, 0.7941 and 0.8757 with the lowest error scores of 0.049, 0.0799, 0.0616 and 0.0353 from the USOD, UFO-120, USOD10K, and DUTS datasets, respectively. The code of our method is available at https://github.com/leckie711/EDMR.
Keywords:
Segmentation network
Underwater environment
Multi-interactive refinement
Salient object detection
Journal
I
IF:
1
Papers:
34
Citations:
0