mlsanityData to 7 Oct 2026

Revisiting Image Pyramid Structure for High Resolution Salient Object Detection

arXiv 2209.09475 ↗First posted 20 Sep 2022cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

Salient object detection (SOD) has been in the spotlight recently, yet has been studied less for high-resolution (HR) images. Unfortunately, HR images and their pixel-level annotations are certainly more labor-intensive and time-consuming compared to low-resolution (LR) images and annotations. Therefore, we propose an image pyramid-based SOD framework, Inverse Saliency Pyramid Reconstruction Network (InSPyReNet), for HR prediction without any of HR datasets. We design InSPyReNet to produce a strict image pyramid structure of saliency map, which enables to ensemble multiple results with pyramid-based image blending. For HR prediction, we design a pyramid blending method which synthesizes two different image pyramids from a pair of LR and HR scale from the same image to overcome effective receptive field (ERF) discrepancy. Our extensive evaluations on public LR and HR SOD benchmarks demonstrate that InSPyReNet surpasses the State-of-the-Art (SotA) methods on various SOD metrics and boundary accuracy.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). Builds on 38 of its 54 references that are in the map. First posted on arXiv 20 Sep 2022.

Builds on

38 of 54 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2022A ConvNet for the 2020scited by 3,545
  7. 2016Pyramid Scene Parsing Networkcited by 2,472
  8. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  9. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  10. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  11. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 549
  12. 2017Structure-measure: A New Way to Evaluate Foreground Mapscited by 480
26 more
  1. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 468
  2. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 452
  3. 2019Axial Attention in Multidimensional Transformerscited by 350
  4. 2020Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentationcited by 326
  5. 2019EGNet:Edge Guidance Network for Salient Object Detectioncited by 237
  6. 2019Kornia: an Open Source Differentiable Computer Vision Library for PyTorchcited by 231
  7. 2019Cascaded Partial Decoder for Fast and Accurate Salient Object Detectioncited by 216
  8. 2020Multi-scale Interactive Network for Salient Object Detectioncited by 212
  9. 2019A Simple Pooling-Based Design for Real-Time Salient Object Detectioncited by 211
  10. 2014The Secrets of Salient Object Segmentationcited by 200
  11. 2021Boundary IoU: Improving Object-Centric Image Segmentation Evaluationcited by 186
  12. 2015Visual Saliency Based on Multiscale Deep Featurescited by 185
  13. 2019F3Net: Fusion, Feedback and Focus for Salient Object Detectioncited by 176
  14. 2021Visual Saliency Transformercited by 175
  15. 2019Salient Object Detection in the Deep Learning Era: An In-Depth Surveycited by 163
  16. 2020Suppress and Balance: A Simple Gated Network for Salient Object Detectioncited by 126
  17. 2018Reverse Attention for Salient Object Detectioncited by 113
  18. 2020CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinementcited by 113
  19. 2020Label Decoupling Framework for Salient Object Detectioncited by 111
  20. 2022Highly Accurate Dichotomous Image Segmentationcited by 110
  21. 2019Towards High-Resolution Salient Object Detectioncited by 92
  22. 2022Pyramid Grafting Network for One-Stage High Resolution Saliency Detectioncited by 63
  23. 2021UACANet: Uncertainty Augmented Context Attention for Polyp Segmentationcited by 61
  24. 2021Deep Automatic Natural Image Mattingcited by 59
  25. 2021Disentangled High Quality Salient Object Detectioncited by 35
  26. 2018Optimizing the F-measure for Threshold-free Salient Object Detectioncited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 14; 2025: 9; 2026: 5.

36 papers.

Sort:

By area:

  1. 2024Bilateral Reference for High-Resolution Dichotomous Image Segmentationcited by 112
  2. 2024SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relightingcited by 66
  3. 2023DreamTuner: Single Image is Enough for Subject-Driven Generationcited by 41
  4. 2024Neural Material Adaptor for Visual Grounding of Intrinsic Dynamicscited by 30
  5. 2024Multi-view Aggregation Network for Dichotomous Image Segmentationcited by 28
  6. 2025Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Datasetcited by 28
  7. 2023Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clippingcited by 17
  8. 2023Recurrent Multi-scale Transformer for High-Resolution Salient Object Detectioncited by 15
  9. 2023DC-Net: Divide-and-Conquer for Salient Object Detectioncited by 12
  10. 2024Ultraman: Single Image 3D Human Reconstruction with Ultra Speed and Detailcited by 12
  11. 2024Zero-Shot Multi-Object Scene Completioncited by 9
  12. 2024AniSora: Exploring the Frontiers of Animation Video Generation in the Sora Eracited by 8
24 more
  1. 2023Salient Object Detection for Images Taken by People With Vision Impairmentscited by 7
  2. 2024High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacitycited by 7
  3. 2025BEN: Using Confidence-Guided Matting for Dichotomous Image Segmentationcited by 7
  4. 2023Uni-Fusion: Universal Continuous Mappingcited by 5
  5. 2024Salient Object-Aware Background Generation using Text-Guided Diffusion Modelscited by 5
  6. 2024BIV-Priv-Seg: Locating Private Content in Images Taken by People With Visual Impairmentscited by 5
  7. 2024HybridBooth: Hybrid Prompt Inversion for Efficient Subject-Driven Generationcited by 5
  8. 2025S3OD: Towards Generalizable Salient Object Detection with Synthetic Datacited by 5
  9. 2023STARS: Zero-shot Sim-to-Real Transfer for Segmentation of Shipwrecks in Sonar Imagerycited by 4
  10. 2025Uncertainty Guided Refinement for Fine-Grained Salient Object Detectioncited by 4
  11. 2024Pluralistic Salient Object Detectioncited by 3
  12. 2024Mixed-Query Transformer: A Unified Image Segmentation Architecturecited by 2
  13. 2023Lightweight high-resolution Subject Matting in the Real Worldcited by 1
  14. 2025High-Precision Dichotomous Image Segmentation via Depth Integrity-Prior and Fine-Grained Patch Strategycited by 1
  15. 2025LawDIS: Language-Window-based Controllable Dichotomous Image Segmentationcited by 1
  16. 2025Loomis Painter: Reconstructing the Painting Processcited by 1
  17. 2024PGNeXt: High-Resolution Salient Object Detection via Pyramid Grafting Networkcited by 0
  18. 2025Weakly Supervised Object Segmentation by Background Conditional Divergencecited by 0
  19. 2025Diverse Signer Avatars with Manual and Non-Manual Feature Modelling for Sign Language Productioncited by 0
  20. 2026Enhancing Adversarial Robustness with Signed Distance Fields for Harmonizing Geometric Invariance and Texturecited by 0
  21. 2026FlowDIS: Language-Guided Dichotomous Image Segmentation with Flow Matchingcited by 0
  22. 2026Saliency-Depth Conditioning for Zero-Shot Segmentation of Communication-Tower Components in Cluttered UAV Imagerycited by 0
  23. 2026HUG-VIS: A Multimodal Benchmark for Human-centered Understanding and Generation in Visual Intelligencecited by 0
  24. 2026IM-ENGINE: Image Editing for Embodied Data Generationcited by 0