mlsanityData to 7 Oct 2026

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

arXiv 2005.09007 ↗First posted 18 May 2020cs.CVcited by 410

Not on the map. Why?

Cited by 41 in Diffusion models, but placed by its own abstract, which didn’t fit.

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.

Key facts. Cited by 410 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 56; 2022: 65; 2023: 89; 2024: 87; 2025: 79; 2026: 34.

410 papers.

Sort:

By area:

  1. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 837
  2. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
  3. 2023AnyDoor: Zero-shot Object-level Image Customizationcited by 411
  4. 2022Kubric: A scalable dataset generatorcited by 373
  5. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  6. 2023TEXTure: Text-Guided Texturing of 3D Shapescited by 303
  7. 2025VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Taskscited by 281
  8. 2023MVImgNet: A Large-scale Dataset of Multi-view Imagescited by 219
  9. 2023EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anythingcited by 187
  10. 2022Sketch-Guided Text-to-Image Diffusion Modelscited by 180
  11. 2021Salient Object Detection via Integrity Learningcited by 133
  12. 2022UIU-Net: U-Net in U-Net for Infrared Small Object Detectioncited by 124
38 more
  1. 2024Bilateral Reference for High-Resolution Dichotomous Image Segmentationcited by 112
  2. 2021Counterfactual Generative Networkscited by 111
  3. 2022Highly Accurate Dichotomous Image Segmentationcited by 110
  4. 2021NeuTex: Neural Texture Mapping for Volumetric Neural Renderingcited by 98
  5. 2024DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generationcited by 93
  6. 2022SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collectionscited by 89
  7. 2021FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attackcited by 74
  8. 2024What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?cited by 74
  9. 2022Pyramid Grafting Network for One-Stage High Resolution Saliency Detectioncited by 63
  10. 2022CLIPascene: Scene Sketching with Different Types and Levels of Abstractioncited by 63
  11. 2024SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentationcited by 63
  12. 2024VideoStudio: Generating Consistent-Content and Multi-Scene Videoscited by 62
  13. 2022Harmonizer: Learning to Perform White-Box Image and Video Harmonizationcited by 61
  14. 2021TransAttUnet: Multi-level Attention-guided U-Net with Transformer for Medical Image Segmentationcited by 60
  15. 2021Deep Automatic Natural Image Mattingcited by 59
  16. 2022CLIPasso: Semantically-Aware Object Sketchingcited by 57
  17. 2024VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Modelscited by 56
  18. 2023DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discoverycited by 53
  19. 2022PANDORA: Polarization-Aided Neural Decomposition Of Radiancecited by 52
  20. 2024TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusioncited by 51
  21. 2022X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusioncited by 49
  22. 2021SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware Inpaintingcited by 48
  23. 2021Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimationcited by 48
  24. 2021Learning to Segment Rigid Motions from Two Framescited by 45
  25. 2022Differentiable Physics Simulation of Dynamics-Augmented Neural Objectscited by 45
  26. 2021Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Networkcited by 42
  27. 2021Boundary-Aware Segmentation Network for Mobile and Web Applicationscited by 41
  28. 2021Automatic Sleep Staging of EEG Signals: Recent Development, Challenges, and Future Directionscited by 41
  29. 2025PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text Renderingcited by 41
  30. 2021DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correctioncited by 38
  31. 2023SAM3D: Segment Anything Model in Volumetric Medical Imagescited by 34
  32. 2021PaddleSeg: A High-Efficient Development Toolkit for Image Segmentationcited by 33
  33. 2021SalientSleepNet: Multimodal Salient Wave Detection Network for Sleep Stagingcited by 31
  34. 2024Object-Centric Diffusion for Efficient Video Editingcited by 31
  35. 2024Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generationcited by 31
  36. 2022Geometric Representation Learning for Document Image Rectificationcited by 26
  37. 2023DS-Fusion: Artistic Typography via Discriminated and Stylized Diffusioncited by 26
  38. 2024Kolmogorov-Arnold Convolutions: Design Principles and Empirical Studiescited by 26

50 most cited of 410 All 410 (JSON)