# U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection

arXiv: https://arxiv.org/abs/2005.09007 · HTML: https://mlsanity.com/paper/2005.09007/

## Key facts

- Cited by 412 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 May 2020.

## Built on by (most cited first, 30 of 412)

- [DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation](https://mlsanity.com/paper/2309.16653/) (2023)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [AnyDoor: Zero-shot Object-level Image Customization](https://mlsanity.com/paper/2307.09481/) (2023)
- [Kubric: A scalable dataset generator](https://mlsanity.com/paper/2203.03570/) (2022)
- [OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation](https://mlsanity.com/paper/2301.07525/) (2023)
- [TEXTure: Text-Guided Texturing of 3D Shapes](https://mlsanity.com/paper/2302.01721/) (2023)
- [VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks](https://mlsanity.com/paper/2504.05118/) (2025)
- [MVImgNet: A Large-scale Dataset of Multi-view Images](https://mlsanity.com/paper/2303.06042/) (2023)
- [EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything](https://mlsanity.com/paper/2312.00863/) (2023)
- [Sketch-Guided Text-to-Image Diffusion Models](https://mlsanity.com/paper/2211.13752/) (2022)
- [Salient Object Detection via Integrity Learning](https://mlsanity.com/paper/2101.07663/) (2021)
- [UIU-Net: U-Net in U-Net for Infrared Small Object Detection](https://mlsanity.com/paper/2212.00968/) (2022)
- [Bilateral Reference for High-Resolution Dichotomous Image Segmentation](https://mlsanity.com/paper/2401.03407/) (2024)
- [Counterfactual Generative Networks](https://mlsanity.com/paper/2101.06046/) (2021)
- [Highly Accurate Dichotomous Image Segmentation](https://mlsanity.com/paper/2203.03041/) (2022)
- [NeuTex: Neural Texture Mapping for Volumetric Neural Rendering](https://mlsanity.com/paper/2103.00762/) (2021)
- [DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generation](https://mlsanity.com/paper/2402.11929/) (2024)
- [SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections](https://mlsanity.com/paper/2205.15768/) (2022)
- [FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attack](https://mlsanity.com/paper/2109.07193/) (2021)
- [What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?](https://mlsanity.com/paper/2403.06090/) (2024)
- [CLIPascene: Scene Sketching with Different Types and Levels of Abstraction](https://mlsanity.com/paper/2211.17256/) (2022)
- [VideoStudio: Generating Consistent-Content and Multi-Scene Videos](https://mlsanity.com/paper/2401.01256/) (2024)
- [SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation](https://mlsanity.com/paper/2408.08870/) (2024)
- [Pyramid Grafting Network for One-Stage High Resolution Saliency Detection](https://mlsanity.com/paper/2204.05041/) (2022)
- [Harmonizer: Learning to Perform White-Box Image and Video Harmonization](https://mlsanity.com/paper/2207.01322/) (2022)
- [TransAttUnet: Multi-level Attention-guided U-Net with Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2107.05274/) (2021)
- [Deep Automatic Natural Image Matting](https://mlsanity.com/paper/2107.07235/) (2021)
- [CLIPasso: Semantically-Aware Object Sketching](https://mlsanity.com/paper/2202.05822/) (2022)
- [VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models](https://mlsanity.com/paper/2403.12034/) (2024)
- [DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery](https://mlsanity.com/paper/2303.09813/) (2023)

## Abstract (arXiv)

In this paper, we design a simple yet powerful deep network architecture, U2-Net, for salient object detection (SOD). The architecture of our U2-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, U2-Net (176.3 MB, 30 FPS on GTX 1080Ti GPU) and U2-Netdagger (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.