mlsanityData to 7 Oct 2026

Deep Gradient Learning for Efficient Camouflaged Object Detection

arXiv 2205.12853 ↗First posted 25 May 2022cs.CVcited by 65

Not on the map. Why?

Abstract (arXiv)

This paper introduces DGNet, a novel deep framework that exploits object gradient supervision for camouflaged object detection (COD). It decouples the task into two connected branches, i.e., a context and a texture encoder. The essential connection is the gradient-induced transition, representing a soft grouping between context and texture features. Benefiting from the simple but efficient framework, DGNet outperforms existing state-of-the-art COD models by a large margin. Notably, our efficient version, DGNet-S, runs in real-time (80 fps) and achieves comparable results to the cutting-edge model JCSOD-CVPR21 with only 6.82% parameters. Application results also show that the proposed DGNet performs well in polyp segmentation, defect detection, and transparent object segmentation tasks. Codes will be made available at https://github.com/GewelsJI/DGNet.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). Builds on 49 of its 85 references that are in the map. First posted on arXiv 25 May 2022.

Builds on

49 of 85 references.

References · 49

  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. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  8. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  9. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  10. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  11. 2019Searching for MobileNetV3cited by 1,984
  12. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,518
37 more
  1. 2019Kvasir-SEG: A Segmented Polyp Datasetcited by 588
  2. 2019UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentationcited by 583
  3. 2017Structure-measure: A New Way to Evaluate Foreground Mapscited by 480
  4. 2020PraNet: Parallel Reverse Attention Network for Polyp Segmentationcited by 460
  5. 2018Enhanced-alignment Measure for Binary Foreground Map Evaluationcited by 370
  6. 2019EGNet:Edge Guidance Network for Salient Object Detectioncited by 237
  7. 2021Anabranch Network for Camouflaged Object Segmentationcited by 227
  8. 2019Cascaded Partial Decoder for Fast and Accurate Salient Object Detectioncited by 216
  9. 2020Multi-scale Interactive Network for Salient Object Detectioncited by 212
  10. 2021Concealed Object Detectioncited by 212
  11. 2021Simultaneously Localize, Segment and Rank the Camouflaged Objectscited by 198
  12. 2020Inf-Net: Automatic COVID-19 Lung Infection Segmentation from CT Imagescited by 184
  13. 2019F3Net: Fusion, Feedback and Focus for Salient Object Detectioncited by 176
  14. 2021Pixel Difference Networks for Efficient Edge Detectioncited by 167
  15. 2021Camouflaged Object Segmentation with Distraction Miningcited by 151
  16. 2022Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detectioncited by 145
  17. 2021Salient Object Detection via Integrity Learningcited by 133
  18. 2015Salient Object Detection: A Benchmarkcited by 130
  19. 2020MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decompositioncited by 127
  20. 2020Structure-Preserving Super Resolution with Gradient Guidancecited by 116
  21. 2021Uncertainty-aware Joint Salient Object and Camouflaged Object Detectioncited by 114
  22. 2021Mutual Graph Learning for Camouflaged Object Detectioncited by 103
  23. 2020Segmenting Transparent Objects in the Wildcited by 98
  24. 2020UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoderscited by 98
  25. 2021Context-aware Cross-level Fusion Network for Camouflaged Object Detectioncited by 86
  26. 2022Video Polyp Segmentation: A Deep Learning Perspectivecited by 81
  27. 2020Highly Efficient Salient Object Detection with 100K Parameterscited by 79
  28. 2021Full-Duplex Strategy for Video Object Segmentationcited by 78
  29. 2021Automatic Polyp Segmentation via Multi-scale Subtraction Networkcited by 77
  30. 2021Progressively Normalized Self-Attention Network for Video Polyp Segmentationcited by 75
  31. 2022Implicit Motion Handling for Video Camouflaged Object Detectioncited by 60
  32. 2020JCS: An Explainable COVID-19 Diagnosis System by Joint Classification and Segmentationcited by 52
  33. 2021Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Networkcited by 42
  34. 2021Boundary-Aware Segmentation Network for Mobile and Web Applicationscited by 41
  35. 2021Deep Texture-Aware Features for Camouflaged Object Detectioncited by 36
  36. 2021Improving Camouflaged Object Detection with the Uncertainty of Pseudo-edge Labelscited by 16
  37. 2021Pedestrian Attribute Recognition in Video Surveillance Scenarios Based on View-attribute Attention Localizationcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 14; 2024: 17; 2025: 17; 2026: 13.

65 papers.

Sort:

By area:

  1. 2023Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applicationscited by 121
  2. 2024Bilateral Reference for High-Resolution Dichotomous Image Segmentationcited by 112
  3. 2023Can SAM Segment Anything? When SAM Meets Camouflaged Object Detectioncited by 99
  4. 2022CamoFormer: Masked Separable Attention for Camouflaged Object Detectioncited by 58
  5. 2022Source-free Depth for Object Pop-outcited by 52
  6. 2022Ponder: Point Cloud Pre-training via Neural Renderingcited by 50
  7. 2023ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detectioncited by 48
  8. 2023Advances in Deep Concealed Scene Understandingcited by 47
  9. 2024A Survey of Camouflaged Object Detection and Beyondcited by 37
  10. 2023Diffusion Model for Camouflaged Object Detectioncited by 27
  11. 2023Chain of Visual Perception: Harnessing Multimodal Large Language Models for Zero-shot Camouflaged Object Detectioncited by 22
  12. 2023CamoDiffusion: Camouflaged Object Detection via Conditional Diffusion Modelscited by 21
38 more
  1. 2024Exploring Deeper! Segment Anything Model with Depth Perception for Camouflaged Object Detectioncited by 20
  2. 2023Referring Camouflaged Object Detectioncited by 19
  3. 2023RFENet: Towards Reciprocal Feature Evolution for Glass Segmentationcited by 19
  4. 2024BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Modelcited by 15
  5. 2024Frontiers in Intelligent Colonoscopycited by 13
  6. 2025Improving SAM for Camouflaged Object Detection via Dual Stream Adapterscited by 13
  7. 2022MFFN: Multi-view Feature Fusion Network for Camouflaged Object Detectioncited by 12
  8. 2024Evaluating SAM2's Role in Camouflaged Object Detection: From SAM to SAM2cited by 12
  9. 2024CamoTeacher: Dual-Rotation Consistency Learning for Semi-Supervised Camouflaged Object Detectioncited by 12
  10. 2025RSAR: Restricted State Angle Resolver and Rotated SAR Benchmarkcited by 12
  11. 2024Explicit Motion Handling and Interactive Prompting for Video Camouflaged Object Detectioncited by 11
  12. 2025UCOD-DPL: Unsupervised Camouflaged Object Detection via Dynamic Pseudo-label Learningcited by 10
  13. 2023Acquiring Weak Annotations for Tumor Localization in Temporal and Volumetric Datacited by 9
  14. 2023Collaborative Camouflaged Object Detection: A Large-Scale Dataset and Benchmarkcited by 8
  15. 2023Large Model Based Referring Camouflaged Object Detectioncited by 8
  16. 2023PrObeD: Proactive Object Detection Wrappercited by 7
  17. 2024Depth Awakens: A Depth-perceptual Attention Fusion Network for RGB-D Camouflaged Object Detectioncited by 7
  18. 2024Unlocking Attributes' Contribution to Successful Camouflage: A Combined Textual and VisualAnalysis Strategycited by 6
  19. 2024COMPrompter: reconceptualized segment anything model with multiprompt network for camouflaged object detectioncited by 6
  20. 2025Deep Learning in Concealed Dense Predictioncited by 6
  21. 2024TS-SAM: Fine-Tuning Segment-Anything Model for Downstream Taskscited by 5
  22. 2024PlantCamo: Plant Camouflage Detectioncited by 5
  23. 2024Adaptive Guidance Learning for Camouflaged Object Detectioncited by 4
  24. 2026HVPNet: A Bio-Inspired Network for General Salient and Camouflaged Object Detectioncited by 4
  25. 2024Towards Real Zero-Shot Camouflaged Object Segmentation without Camouflaged Annotationscited by 3
  26. 2025Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentationcited by 3
  27. 2025Distribution-Specific Learning for Joint Salient and Camouflaged Object Detectioncited by 3
  28. 2025SCOUT: Semi-supervised Camouflaged Object Detection by Utilizing Text and Adaptive Data Selectioncited by 3
  29. 2023When Super-Resolution Meets Camouflaged Object Detection: A Comparison Studycited by 1
  30. 2025MSVCOD:A Large-Scale Multi-Scene Dataset for Video Camouflage Object Detectioncited by 1
  31. 2025Scoring, Remember, and Reference: Catching Camouflaged Objects in Videoscited by 1
  32. 2025LawDIS: Language-Window-based Controllable Dichotomous Image Segmentationcited by 1
  33. 2025GAPNet: A Lightweight Framework for Image and Video Salient Object Detection via Granularity-Aware Paradigmcited by 1
  34. 2025RealCamo: Boosting Real Camouflage Synthesis with Layout Controls and Textual-Visual Guidancecited by 1
  35. 2026Weakly Supervised Camouflaged Object Detection Based on the SAM Model and Mask Guidancecited by 1
  36. 2024Shifting Spotlight for Co-supervision: A Simple yet Efficient Single-branch Network to See Through Camouflagecited by 0
  37. 2024Scale-Invariant Object Detection by Adaptive Convolution with Unified Global-Local Contextcited by 0
  38. 2025Green Video Camouflaged Object Detectioncited by 0

50 most cited of 65 All 65 (JSON)