Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection

About

In this paper, we design a simple yet powerful deep network architecture, U$^2$-Net, for salient object detection (SOD). The architecture of our U$^2$-Net is a two-level nested U-structure. The design has the following advantages: (1) it is able to capture more contextual information from different scales thanks to the mixture of receptive fields of different sizes in our proposed ReSidual U-blocks (RSU), (2) it increases the depth of the whole architecture without significantly increasing the computational cost because of the pooling operations used in these RSU blocks. This architecture enables us to train a deep network from scratch without using backbones from image classification tasks. We instantiate two models of the proposed architecture, U$^2$-Net (176.3 MB, 30 FPS on GTX 1080Ti GPU) and U$^2$-Net$^{\dagger}$ (4.7 MB, 40 FPS), to facilitate the usage in different environments. Both models achieve competitive performance on six SOD datasets. The code is available: https://github.com/NathanUA/U-2-Net.

Xuebin Qin, Zichen Zhang, Chenyang Huang, Masood Dehghan, Osmar R. Zaiane, Martin Jagersand• 2020

Related benchmarks

TaskDatasetResultRank
Salient Object DetectionDUTS (test)
M (MAE)0.044
357
Salient Object DetectionECSSD
MAE0.033
226
Salient Object DetectionPASCAL-S
MAE0.074
196
Salient Object DetectionHKU-IS
MAE0.031
179
Salient Object DetectionDUT-OMRON
MAE0.054
137
Salient Object DetectionHKU-IS (test)
MAE0.031
137
Salient Object DetectionECSSD (test)
S-measure (Sa)0.927
104
Salient Object DetectionDUT-OMRON (test)
MAE0.054
92
Medical Image SegmentationISIC
DICE82.25
79
Salient Object DetectionECSSD 1,000 images (test)
MAE0.033
68
Showing 10 of 76 rows
...

Other info

Code

Follow for update