Research

Salient Objects in Clutter

Deng-Ping Fan

Abstract

This paper provides a comprehensive evaluation of salient object detection (SOD) models. Our analysis identifies a serious design bias of existing SOD datasets, assuming that each image contains at least one outstanding salient object in low clutter. This is an unrealistic assumption. When evaluated on existing datasets, the design bias has led to a saturated high performance for state-of-the-art SOD models. The models, however, still perform far from being satisfactory when applied to real-world daily scenes. Based on our analyses, we first identify seven crucial aspects that a comprehensive and balanced dataset should fulfill. Then, we propose a new high-quality dataset and update the previous saliency benchmark. Specifically, our SOC dataset, Salient Objects in Clutter, includes images with salient and non-salient objects from daily object categories. Beyond object category annotations, each salient image is accompanied by attributes (e.g., appearance change, clutter) that reflect common challenges in real-world scenes and can help 1) gain a deeper insight into the SOD problem, 2) investigate the pros and cons of the SOD models, and 3) objectively assess models from different perspectives. Finally, we report an attribute-based performance assessment on our SOC dataset. We believe that our dataset and results will open new directions for future research on salient object detection.

Github

Paper

  1. Salient Objects in Clutter, Deng-Ping Fan, Jing Zhang, Gang Xu, Ming-Ming Cheng*, and Ling Shao, IEEE TPAMI, 2022. [pdf |  bib  | 中译版 | Benchmark]
  2. Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground, Deng-Ping Fan, Ming-Ming Cheng*, Jiang-Jiang Liu, Shang-Hua Gao, Qibin Hou, Ali Borji, ECCV, 2018. [pdf | 中译版 | project | evaluate code | Dataset  (730.2MB):  Baidu, Google]

Most related projects on this website

Please cite the related paper if you use our results

@article{fan2022clutter,
  title={Salient Objects in Clutter},
  author={Fan, Deng-Ping and Zhang, Jing and Xu, Gang and Cheng, Ming-Ming and Shao, Ling},
  journal={IEEE TPAMI},
  year={2022}
}

@article{Cheng2021sMeasure,
  title={Structure-measure: A New Way to Evaluate Foreground Maps},
  author={Ming-Ming Cheng and Deng-Ping Fan},
  journal={International Journal of Computer Vision (IJCV)},
  year={2021},
  volume={129},
  number={9},
  pages={2622-2638},
  doi = {10.1007/s11263-021-01490-8},
}

@inproceedings{Fan2018Enhanced,
  author={Deng-Ping Fan, Cheng Gong, Yang Cao, Bo Ren, Ming-Ming Cheng, Ali Borji},
  title={{Enhanced-alignment Measure for Binary Foreground Map Evaluation}},
  booktitle={International Joint Conference on Artificial Intelligence (IJCAI)},
  pages = {698-704},
  year={2018}
}

Contact

If you have any questions, drop us an e-mail at <dengpingfan@mail.nankai.edu.cn>.

If you are interested in salient object detection technology,  we are happy to invite you to join our community (QQ: 229286817). There are hundreds of active researchers here.

Add Your Model to this Benchmark

If you want to list your results on our web, please send your name, model name, paper title, short description of your method and the link of the web of your project (if you have).

Important Tips

Note that some works use the so-called same F-measure metric, while they do not explicitly describe which statistic (e.g., mean or max) they used, easily resulting in unfair comparison and inconsistent performance. Meanwhile, the different threshold strategies in F-measure (e.g., 255 varied thresholds, adaptive saliency threshold, and self-adaptive threshold) will result in different performances. Fairly comparing RGB-D-based SOD models by extensively evaluating them with the same metrics on standard benchmarks is highly desired.

So you need to download all of our re-organized datasets and saliency maps of each model and then evaluate your model.

Evaluation Code

RGBDBenchmark-EvaluationTools.zip  [Baidu (fetch code: i09j)|Google Drive] (updated in 2019/7/18)

SOC dataset

Note that the Test Set only contains images and without ground truth.  We will create the  SOC Benchmark website soon, and you can upload your result to obtain the final score on our website. Also, you can use the Validation Set as Test Set first. Note that the image file of COCO_train2014_000000080168.PNG should be changed with the new file name COCO_train2014_000000080168.png to prevent some errors while training your model.

  • Overall 6K SOC Dataset  (730.2MB)  [Baidu] [Google]
  • 3.6K SOC Training Set (441.32MB) [Baidu] [Google]
  • 1.2K  SOC Validation Set (146.56MB) [Baidu] [Google]
  • 1.2K  SOC Test Set (141.86MB) [Baidu] [Google]
  • Object-level Ground-Truth of the SOC Test Set released. [Baidu pan] [update: 2019/08/15]
  • Instance-level Ground-Truth of the SOC Test Set released [Baidu pan] [update: 2019/08/15

Object-level Salient Object Detection datasets

Note that: If you downloaded the dataset, please cite the related citation in your paper. These datasets are only for academic convenience.

Overall [baidu pan]

  1. THUR-15K [baidu pan]
  2. DUTS [baidu pan]
  3. MSRA-B [baidu pan]
  4. MSRA-10K (THUS10K) [baidu pan]
  5. DUT-OMROM [baidu pan]
  6. PASCAL-S [baidu pan]
  7. HKU-IS [baidu pan]
  8. ECSSD [baidu pan]
  9. Judd-A [baidu pan] (fetch code: lqbc)
  10. SOD [baidu pan]
  11. SED2 [baidu pan]
  12. SOC [baidu pan] (ECCV 2018)
  13. HDSOD2K [baidu pan] (ICCV 2019)  coming soon 🙂
  14. Nighttime Image (NI) dataset (CVPRW 2019) is coming soon 🙂
  15. LightFieldSOD [baidu pan] (ICCV 2019) coming soon 🙂
  16. RSI dataset (TGRS 2019)   [800 remote sensing images] coming soon 🙂

There are so many SOD datasets; please enjoy them.

Traditional Methods (update: 2019-12-20)

  1. [It][1998][PAMI] A Model of Saliency-Based Visual Attention for Rapid Scene Analysis,
  2. [FG][2003][ACMMM]Contrast-based image attention analysis by using fuzzy growing,
  3. [RSA][2005][ACMMM]Robust subspace analysis for detecting visual attention regions in images,
  4. [AIM][2005][NIPS]Saliency Based on Information Maximization,
  5. [RE][2006][ICME]Region enhanced scale-invariant saliency detection,
  6. [SR]  [2007][CVPR]Saliency Detection A Spectral Residual Approach,
  7. [GB][2007][NIPS]Graph-Based Visual Saliency,
  8. [RU][2007][TMM]A rule based technique for extraction of visual attention regions based on real-time clustering,
  9. [SUN][2008][JOV]SUN: A bayesian framework for saliency using natural statistics,
  10. [AC][2008][ICVS]Salient region detection and segmentation,
  11. [FT][2009][CVPR]Frequency-tuned Salient Region Detection,
  12. [ICC][2009][ICCV]Image saliency by isocentric curvedness and color,
  13. [EDS][2009][PR]simple method for detecting salient regions,
  14. [CA][2010][CVPR]Context-Aware Saliency Detection,
  15. [SEG][2010][ECCV]Segmenting Salient Objects from Images and Videos,
  16. [MSSS][2010][ICIP]Saliency Detection using Maximum Symmetric Surround,
  17. [CSM][2010][ACMMM]Automatic interesting object extraction from images using complementary saliency maps,
  18. [HC,RC][2011][CVPR]Global Contrast based Salient Region Detection,
  19. [SVO][2011][ICCV]Fusing generic objectness and visual saliency for salient object detection,
  20. [CSD][2011][ICCV]Center-surround divergence of feature statistics for salient object detection,
  21. [CC][2011][ICCV]Salient object detection using concavity context,
  22. [CB][2011][BMVC]Automatic Salient Object Segmentation Based on Context and Shape Prior,
  23. [SF][2012][CVPR]Saliency Filters Contrast Based Filtering for Salient Region Detection,
  24. [LR][2012][CVPR]A Unified Approach to Salient Object Detection via Low Rank Matrix Recovery,
  25. [GS][2012][ECCV]Geodesic saliency using background priors,
  26. [BSF][2012][ICIP]Saliency Detection Based on Integration of Boundary and Soft-Segmentation,
  27. [GC,GU][2013][ICCV]Efficient Salient Region Detection with Soft Image Abstraction,
  28. [MR][2013][CVPR]Saliency Detection via Graph-Based Manifold Ranking,
  29. [MC][2013][ICCV]Saliency Detection via Absorbing Markov Chain,
  30. [DRFI][2013][CVPR]Salient Object Detection A Discriminative Regional Feature Integration Approach,
  31. [DSR][2013][ICCV]Saliency Detection via Dense and Sparse Reconstruction,
  32. [PISA][2013][CVPR]Pisa: Pixelwise image saliency by aggregating complementary appearance contrast measures with spatial priors,
  33. [CRF][2013][CVPR]Saliency aggregation: A data-driven approach,
  34. [HS][2013][CVPR]Hierarchical Saliency Detection,
  35. [PCA][2013][CVPR]What Makes a Patch Distinct,
  36. [STD][2013][CVPR]Statistical textural distinctiveness for salient region detection in natural images,
  37. [CRF][2013][CVPR]Saliency Aggregation A Data-driven Approach,
  38. [SUB][2013][CVPR]Submodular salient region detection,
  39. [UFO][2013][ICCV]Salient Region Detection by UFO Uniqueness, Focusness and Objectness,
  40. [CHM][2013][ICCV]Contextual hypergraph modeling for salient object detection,
  41. [COV][2013][JOV]Visual saliency estimation by nonlinearly integrating features using region covariances,
  42. [CIO][2013][ICCV]Category-independent object-level saliency detection,
  43. [GR][2013][SPL]Graph-Regularized Saliency Detection With Convex-Hull-Based Center Prior,
  44. [SLMR][2013][BMVC]Segmentation driven lowrank matrix recovery for saliency detection,
  45. [LSSC][2013][TIP]Bayesian Saliency via Low and Mid Level Cues,
  46. [LSMD][2013][AAAI]Salient object detection via low-rank and structured sparse matrix decomposition,
  47. [HDCT][2014][CVPR]Salient Region Detection via High-Dimensional Color Transform,
  48. [PDE][2014][CVPR]Adaptive partial differential equation learning for visual saliency detection,
  49. [RBD][2014][CVPR]Saliency Optimization from Robust Background Detection,
  50. [MSS][2014][SPL]Saliency Detection with Multi-Scale Superpixels,
  51. [GP][2015][ICCV]Generic Promotion of Diffusion-Based Salient Object Detection,
  52. [MBS][2015][ICCV]Minimum Barrier Salient Object Detection at 80 FPS,
  53. [WSC][2015][CVPR]A Weighted Sparse Coding Framework for Saliency Detection,
  54. [RRW][2015][CVPR]Robust saliency detection via regularized random walks ranking,
  55. [TLLT][2015][CVPR]Saliency Propagation from Simple to Difficult,
  56. [BL][2015][CVPR]Salient Object Detection via Bootstrap Learning,
  57. [BSCA][2015][CVPR]Saliency Detection via Cellular Automata,
  58. [GLC][2015][PR]Salient Object Detection via Global and Local Cues,
  59. [LPS][2015][TIP]Inner and Inter Label Propagation Salient Object Detection in the Wild,
  60. [MAPM][2015][TIP]Saliency Region Detection based on Markov Absorption Probabilities,
  61. [NCS][2015][TIP]Normalized cut-based saliency detection by adaptive multi-level region merging,
  62. [BFS][2015][NC]Saliency Detection via Background and Foreground Seed Selection,
  63. [UF][2016][TMM]A Universal Framework for Salient Object Detection,
  64. [MST][2016][CVPR]Real-Time Salient Object Detection with a Minimum Spanning Tree,
  65. [PM][2016][ECCV]【post-processing method】Pattern Mining Saliency,
  66. [DSP][2016][PR]Discriminative saliency propagation with sink points,
  67. [EBM][2016][IJCAI]Saliency Transfer An Example-Based Method for Salient Object Detection,
  68. [AWC][2016][Neurocomputing]Robust manifold-preserving diffusion-based saliency detection by adaptive weight construction,
  69. [MRMF][2016][TNNLS] Manifold Ranking-Based Matrix Factorization for Saliency Detection,
  70. [SBCRF][2017][Neurocomputing]A superpixel-based CRF saliency detection approach,
  71. [WLRR][2017][SPL]Salient Object Detection via Weighted Low Rank Matrix Recovery,
  72. [MIL][2017][TIP]Salient Object Detection via Multiple Instance Learning,
  73. [SMD][2017][PAMI]Salient Object Detection via Structured Matrix Decomposition,
  74. [MDC][2017][TIP]300-FPS Salient Object Detection via Minimum Directional Contrast,[code]
  75. [SS][2017][NC]Spectral Salient Object Detection,
  76. [IFC][2017][TMM]Iterative Feedback Control Based Salient Object Segmentation,
  77. [CCRF][2017][TMM]Saliency Detection by Fully Learning A Continuous Conditional Random Field,
  78. [ELER][2017][CVPR]What is and what is not a salient object? learning salient object detector by ensembling linear exemplar regressors,
  79. [DIMD][2017][PR]Diversity Induced Matrix Decomposition Model for salient object detection,
  80. [ProS][2018][NC]ProS]Salient Object Detection via Proposal Selection,
  81. [WMR][2018][NC]Saliency detection via affinity graph learning and weighted manifold ranking,
  82. [RCRR][2018][TIP]Reversion correction and regularized random walk ranking for saliency detection,
  83. [JLSE][2018][TIP] Exemplar-aided Salient Object Detection via Joint Latent Space Embedding,
  84. [WFD][2018][PR]Water flow driven salient object detection at 180 fps,
  85. [FBQ][2018][Access]Hypergraph Optimization for Salient Region Detection Based on Foreground and Background Queries,
  86. [FTOE][2019][TMM]Salient Object Detection via Fuzzy Theory and Object-level Enhancement,
  87. [KSR][2019][TIP]Visual Saliency Detection via Kernelized Subspace Ranking with Active Learning, (SOC)
  88. [FCB][2019][TIP]Exploiting Color Volume and Color Difference for Salient Region Detection,
  89. [TSG][2019][TCSVT]Salient Object Detection Via Two-Stage Graphs,
  90. [DSC][2019][TCSVT]Direction Selective Contour Detection for Salient,
  91. [AIGC][2019][TCSVT]Adaptive Irregular Graph Construction Based Salient Object Detection,
  92. [PDP][2019][TIP]RGB-‘D’ Saliency Detection With Pseudo Depth,
  93. [NIO][2019][TNNLS] Semisupervised Learning Based on a Novel Iterative Optimization Model for Saliency Detection,
  94. [MSR][2019][TIP]50 FPS Object-Level Saliency Detection via Maximally Stable Region
  95. [MSGC][2019][TMM]Saliency Detection via Multi-Scale Global Cues,
  96. [LRR][2019][TIP]Local Regression Ranking for Saliency Detection,

…..

Note that SOC contains many non-salient images. The ground truth is all zero matrices; thus, directly using the F-measure may result in a very low inaccurate score. We only list the S-measure, max E-measure, and MAE scores in our benchmark.

CNN based Methods from 2015-current  (update: 2019-12-20)

  1. SuperCNN: A superpixelwise convolutional neural network for salient object detection, IJCV, 2015.
  2. LEGS: Deep networks for saliency detection via local estimation and global search, Wang, L. et al, CVPR, 2015.
  3. MC: Saliency detection by multi-context deep learning, Zhao, R., et al, CVPR, 2015.
  4. MDF: Visual saliency based on multiscale deep features, Li, G., et al, CVPR, 2015.
  5. DISC: DISC: Deep image saliency computing via progressive representation learning,  Chen, T., et al,  TNNLS, 2016.
  6. DSL: Dense and Sparse Labeling with Multi-Dimensional Features for Saliency Detection, Yucheng, TCSVT, 2016.
  7. DS: DeepSaliency: Multi-task deep neural network model for salient object detection, Li, X., et al, TIP, 2016.
  8. SSD: A shape-based approach for salient object detection using deep learning, ECCV, 2016.
  9. CRPSD: Saliency Detection via Combining Region-Level and Pixel-Level Predictions with CNNs, ECCV, 2016.
  10. RFCN: Saliency detection with recurrent fully convolutional networks, Wang, L., et al,  ECCV, 2016.
  11. RFCN: Salient object detection with recurrent fully convolutional networks, TPAMI, 2019.
  12. MAP: Unconstrained salient object detection via proposal subset optimization, CVPR, 2016.
  13. SU: Saliency unified: A deep architecture for simultaneous eye fixation prediction and salient object segmentation, CVPR, 2016.
  14. RACDNN: Recurrent attentional networks for saliency detection, CVPR, 2016.
  15. ELD: Deep Saliency with Encoded Low level Distance Map and High Level Features, Gayoung, L., et al, CVPR, 2016.
  16. DHS: DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection, Liu, N., et al, CVPR, 2016.
  17. DCL: Deep Contrast Learning for Salient Object Detection, Li, G.,et al, CVPR, 2016.
  18. DSRCNN: Deeply-Supervised Recurrent Convolutional Neural Network for Saliency Detection, MM, 2016.
  19. MSCNet: Multi-Scale Cascade Network for Salient Object Detection, MM, 2017.
  20. CAR: Salient object detection using a context-aware refinement network, BMVC, 2017.
  21. IMC: Deep Salient Object Detection by Integrating Multi-level Cues, Zhang, J., et al, WACV 2017.
  22. DLS: Deep Level Sets for Salient Object Detection, CVPR, 2017.
  23. MSRNet: Instance-Level Salient Object Segmentation, Li, G., et al, CVPR, 2017.
  24. WSS: Learning to Detect Salient Objects with Image-level Supervision, CVPR, 2017.
  25. SRM: A stagewise refinement model for detecting salient objects in images, CVPR, 2017.
  26. NLDF: Non-local deep features for salient object detection, Luo, Z., et al, CVPR, 2017.
  27. DSS: Deeply supervised salient object detection with short connections, Hou, Q., et al, CVPR, 2017/TPAMI, 2019.
  28. FSN: Look, perceive and segment: Finding the salient objects in images via two-stream fixation-semantic cnns, ICCV, 2017.
  29. DSOS: Delving into Salient Object Subitizing and Detection, ICCV, 2017.
  30. SVF: Supervision by fusion: Towards unsupervised learning of deep salient object detector, ICCV, 2017.
  31. UCF: Learning Uncertain Convolutional Features for Accurate Saliency Detection, Zhang, P., et al, ICCV, 2017.
  32. AMU: Amulet: Aggregating multi-level convolutional features for salient object detection, Zhang, P., et al, ICCV, 2017.
  33. UGA: An Unsupervised Game-Theoretic Approach to Saliency Detection, TIP, 2018.
  34. Refinet: Refinet A deep segmentation assisted refinement network for salient object detection, TMM, 2019.
  35. MSED: Multi-scale deep encoder-decoder network for salient object detection, Neurocomputing, 2018.
  36. EARNet: Embedding Attention and Residual Network for Accurate Salient Object Detection, Cybernetics, 2018
  37. BFANet: Boundary-Guided Feature Aggregation Network for Salient Object Detection, SPL, 2018.
  38. LICNN: Lateral inhibition-inspired convolutional neural network for visual attention and
    saliency detection, AAAI, 2018.
  39. ASMO: Weakly supervised salient object detection using image labels, AAAI, 2018.
  40. RADF: Recurrently aggregating deep features for salient object detection, AAAI, 2018.
  41. R3Net: Recurrent Residual Refinement Network for Saliency Detection, IJCAI,  2018.
  42. HDFP: Holistic and Deep Feature Pyramids for Saliency Detection, BMVC, 2018.
  43. C2SNet: Contour Knowledge Transfer for Salient Object Detection, ECCV, 2018.
  44. RAS: Reverse Attention for Salient Object Detection, ECCV, 2018.
  45. LPSNet: Learning to Promote Saliency Detectors, CVPR, 2018.
  46. RSOD: Revisiting salient object detection: Simultaneous detection, ranking, and subitizing of multiple salient objects, CVPR, 2018.
  47. DUS: Deep unsupervised saliency detection: A multiple noisy labeling perspective, CVPR, 2018.
  48. ASNet: Salient Object Detection Driven by Fixation Prediction, CVPR, 2018.
  49. ASNet: Inferring Salient Objects from Human Fixations, Wang etal, TPAMI 2019.
  50. BDMPM: A Bi-directional Message Passing Model for Salient Object Detection, CVPR, 2018.
  51. DGRL: Detect globally, refine locally: A novel approach to saliency detection, CVPR, 2018.
  52. PiCANet: Learning pixel-wise contextual attention for saliency detection, CVPR, 2018.
  53. PAGRN: Progressive attention guided recurrent network for salient object detection, CVPR, 2018.
  54. SD: Super Diffusion for Salient Object Detection, TIP, 2019.
  55. EANet: Enhancing Salient Object Segmentation Through Attention, arXiv, 2019.
  56. RRNet: Region Refinement Network for Salient Object Detection, arXiv, 2019.
  57. ROSA: Robust Salient Object Detection against Adversarial Attacks, TYCB, 2019.
  58. SAC-Net: Spatial Attenuation Context for Salient Object Detection, arXiv, 2019.
  59. Troy: Give Attention to Saliency and for Saliency, arXiv, 2018.
  60. Agile amulet: Real-time salient object detection with contextual attention, arXiv, 2018.
  61. OGNet: Salient Object Detection with Output-guided Attention Module, arXiv, 2019.
  62. Contour Loss: Boundary-Aware Learning for Salient Object Segmentation, arXiv, 2019.
  63. SE2Net: Siamese Edge-Enhancement Network for Salient Object Detection, arXiv, 2019.
  64. DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detection, arXiv, 2019.
  65. DRMC: Deep Reasoning with Multi-scale Context for Salient Object Detection, arXiv, 2019.
  66. RDSNet: Richer and Deeper Supervision Network for Salient Object Detection, arXiv, 2019.
  67. SSL: Saliency based Semi-supervised Learning for Orbiting Satellite Tracking, arXiv, 2019.
  68. EGNL: Edge-guided Non-local Fully Convolutional Network for Salient Object Detection, arXiv, 2019.
  69. DSAL-GAN: Denoising Based Saliency Prediction with Generative Adversarial Networks, arXiv, 2019.
  70. CAGNet: Content-Aware Guidance for Salient Object Detection, arXiv, 2019.
  71. SaLite : A light-weight model for salient object detection, arXiv, 2019. (SOC)
  72. RecNet: Exploring Reciprocal Attention for Salient Object Detection by Cooperative Learning, arXiv, 2019.
  73. RTGRNet: Boundary-Aware Salient Object Detection via Recurrent Two-Stream Guided Refinement Network, arXiv, 2019.
  74. DANet: Distortion-adaptive Salient Object Detection in 360∘ Omnidirectional Images, Jia Li, JSTSP, 2019.
  75. Three Birds One Stone: A General Architecture for Salient Object Segmentation, Edge Detection and Skeleton Extraction, arXiv, 2019.
  76. RSR: Relative Saliency and Ranking: Models, Metrics, Data and Benchmarks, TPAMI, 2019.
  77. HBR: A hybrid-backward refinement model for salient object detection, Neurocomputing, 2019.
  78. EANet: Edge-Aware Convolution Neural Network Based Salient Object Detection, SPL, 2019.
  79. GCBR: Salient Object Detection in Low Contrast Images via Global Convolution and Boundary Refinement, CVPRW, 2019.
  80. HyperFusion-Net: Densely Reflective Fusion for Salient Object Detection, Pingping Zhang et al, PR, 2019.
  81. Deepside: Deepside A General Deep Framework for Salient Object Detection, Neurocomputing, 2019. (SOC)
  82. LFRWS: Salient Object Detection with Lossless Feature Reflection and Weighted Structural Loss, TIP, 2019.
  83. LVNet: Nested Network with Two-Stream Pyramid for Salient Object Detection in Optical Remote Sensing Images, TGRS, 2019.
  84. FBG: Focal Boundary Guided Salient Object Detection, TIP, 2019.
  85. CCAL: Salient Object Detectioin Using Cascaded Convolutional Neural Networks and Adversarial Learning, TMM, 2019.
  86. ConnNet: A Long-Range Relation-Aware Pixel-Connectivity Network for Salient Segmentation, TIP, 2019.
  87. CIG: Deep Salient Object Detection with Contextual Information Guidance, TIP, 2020.
  88. SPA: Semantic Prior Analysis for Salient Object Detection, TIP, 2019.
  89. SIA: Saliency Integration An Arbitrator Model, TMM, 2019.
  90. CDMG: Weakly Supervised Salient Object Detection by Learning A Classifier-Driven Map Generator, TIP, 2019.
  91. MIJR: Salient Object Detection via Multiple Instance Joint Re-Learning, TCSVT, 2019.
  92. CRA: RGBT Salient Object Detection: Benchmark and A Novel Cooperative Ranking Approach, TCSVT, 2019. (RGB-T)
  93. AADF: Aggregating Attentional Dilated Features for Salient Object Detection, TCSVT, 2019.
  94. LFCS: Semi-Supervised Salient Object Detection Using a Linear Feedback Control System Model, TCYB, 2019. (wFb)
  95. SSNet (ICCV 2015 SVF extented): Synthesizing Supervision for Learning Deep Saliency Network without Human Annotation, TPAMI, 2019.
  96. ANDA: A Novel Data Augmentation Technique Applied to Salient Object Detection, ICAR, 2019.
  97. DEF: Deep Embedding Features for Salient Object Detection, AAAI, 2019.
  98. SuperVAE: Superpixelwise Variational Autoencoder for Salient Object Detection, Bo Li et al, AAAI, 2019.
  99. CapSal: Leveraging Captioning to Boost Semantics for Salient Object Detection, Lu Zhang et al, CVPR, 2019. (SOC)
  100. BASNet: Boundary-Aware Salient Object Detection, CVPR, 2019.
  101. PFANet: Pyramid Feature Attention Network for Saliency Detection, CVPR, 2019.
  102. MWS: Multi-source weak supervision for saliency detection, Yu Zeng et al, CVPR, 2019.
  103. ICNet: An Iterative and Cooperative Top-down and Bottom-up Inference Network for Salient Object Detection, W. Wang et al, CVPR, 2019.
  104. PAGE-Net: Salient Object Detection with Pyramid Attention and Salient Edge, Wenguan Wang et al, CVPR, 2019.
  105. CPD: Cascaded Partial Decoder for Fast and Accurate Salient Object Detection, CVPR, 2019.
  106. MLMSNet: A Mutual Learning Method for Salient Object Detection with intertwined Multi-Supervision, Runming Wu et al, CVPR, 2019.
  107. AFNet: Attentive Feedback Network for Boundary-Aware Salient Object Detection, Mengyang Feng et al, CVPR, 2019.
  108. DPOR: Employing Deep Part-Object Relationships for Salient Object Detection, ICCV, 2019.
  109. SIBA: Selectivity or Invariance Boundary-aware Salient Object Detection, ICCV, 2019.
  110. JDF: Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection, ICCV, 2019.
  111. JLNet: Joint learning of saliency detection and weakly supervised semantic segmentation,Yu Zeng, ICCV, 2019.
  112. OFM: Optimizing the F-Measure for Threshold-Free Salient Object Detection, ICCV, 2019.
  113. GFLN: Towards High-Resolution Salient Object Detection, Z. Yi et al, ICCV, 2019.
  114. DMRA: Depth-induced Multi-scale Recurrent Attention Network for Saliency Detection, Yongri Piao, ICCV 2019.
  115. DLLF: Deep Learning for Light Field Saliency Detection, Tiantian Wang, ICCV, 2019.
  116. EGNet: Edge Guidance Network for Salient Object Detection, JX. Zhao etal, ICCV, 2019.
  117. SCRNet: Stacked Cross Refinement Network for Edge-Aware Salient Object Detection, Z.Wu et al. ICCV, 2019. (SOC)
  118. DeepUSPS: Deep Robust Unsupervised Saliency Prediction With Self-Supervision, T Nguyen, NIPS, 2019.  (Unsupervised)
  119. MOD: Memory-oriented Decoder for Light Field Salient Object Detection, Huchuan Lu, NIPS, 2019. (Light Field)
  120. FMCF: RGB-T Salient Object Detection via Fusing Multi-level CNN Features, 2019, TIP. (S-m, wF-m)
  121. EAI: Efficient Saliency Maps for Explainable AI, ICLR, 2020. (Explainable saliency)
  122. PFPNet: Progressive Feature Polishing Network for Salient Object Detection， AAAI,2020.
  123. F3Net: Fusion, Feedback and Focus for Salient Object Detection, AAAI, 2020. (S-m, E-m, mean F-m)

….

Note that: If the model is used, S-measure will be marked with color; the used E-measure will be marked with color; the used weighted F-measure will be marked with ltalic.

(update: 2019/08/27)

SCRNet Results: [pdf]

SOC-test Object-level Salient Object Detection Leaderboard (Deep Models)

Please refer to https://github.com/mczhuge/ICON

(Visited 8,957 times, 2 visits today)
Subscribe
Notify of
guest

9 Comments
Inline Feedbacks
View all comments
trackback

betting tips premier league

blog topic

0
Reply
trackback

flitch beam

Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground – 程明明个人主页

0
Reply
trackback

shaded white farrow and ball

Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground – 程明明个人主页

0
Reply
trackback

magento agency

Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground – 程明明个人主页

0
Reply
trackback

hollow strapon

Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground – 程明明个人主页

0
Reply
trackback

blocked drains birmingham

blog topic

0
Reply
trackback

firming eye cream

Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground – 程明明个人主页

0
Reply
S.B.

How can we evaluate our results in SOC test dataset ?

0
Reply
MM Cheng

You can contact dengpingfan@mail.nankai.edu.cn to get help on this issue.

0
Reply
wpdiscuz   wpDiscuz 
@article{fan2022clutter,
  title={Salient Objects in Clutter},
  author={Fan, Deng-Ping and Zhang, Jing and Xu, Gang and Cheng, Ming-Ming and Shao, Ling},
  journal={IEEE TPAMI},
  year={2023},  
  volume={45},
  number={2},
  pages={2344-2366},  
  doi={10.1109/TPAMI.2022.3166451}, 
}
Powered by