Algorithm

Residual

Network architecture

Philosophy

Object detection

Net (polyhedron)

Set (abstract data type)

Parallel computing

Computer science

Visual arts

Simple (philosophy)

Code (set theory)

Architecture

Computer network

Pooling

Computer architecture

Pattern recognition (psychology)

Mathematics

Epistemology

Computer engineering

Scratch

Artificial intelligence

Geometry

Programming language

Salient

Pattern Recognition

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.

U2-Net: Going deeper with nested U-structure for salient object detection