Authors: Deng-Ping Fan, Jing Zhang, Gang Xu, Ming-Ming Cheng, Ling Shao.
-
This repository provides benchamrk for "Salient objects in clutter". (paper | 中文版)
-
If you have any questions about our paper, feel free to contact me. And if you are using SOCbenchamrk results or evaluation toolbox for your research, please cite this paper (BibTeX).
Salient object detection (SOD) originated from the task of fixation prediction (FP), switching attention regions for accurate object-level regions.
Current algorithms have been developed for 2D images of limited resolution (width or height
Recently, several interesting extensions of SOD have also been introduced, such as salient instance detection (SID),
salient object subitizing (SOS), and saliency ranking.
A taxonomy of the saliency detection task is shown below.
Different from previous SOD reviews, we mainly focus on 2D salient object detection in a fully supervised manner. We highlight the scope of this study in gray.
For other closely related 3D/4D SOD tasks, we refer readers to
recent survey and benchmarking works such as RGB-D SOD, Event-RGB SOD (ERSOD), Light Field SOD,
Co-SOD, 360° Video SOD, and Video SOD.
Fig.1 Taxonomy of the saliency detection task. We highlight the scope of this study in gray.
Link: https://github.com/mczhuge/SOCToolbox Note: If you want to list your results on our web, please send your name, model name, paper title to us. Important Tips: 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 performance. Fairly comparing RGB-D based SOD models by extensively evaluating them with same metrics on standard benchmarks is highly desired. So you need to download all of our re-organized datasets, saliency maps of each model and then evaluate your model.
Fig.2 Examples from our new SOCdataset,including non-salient (first row) and salient object images (rows 2 to 4). For salient object images, an instance-level ground-truth map (different color), object attributes (Attr) and category labels are provided.
Fig.3 (a) Number of annotated instances per category in our SOC dataset. (b, c) Global and local color contrast statistics, respectively. (d) A set of saliency maps from our dataset and their overlay map. (e) Location distribution of the salient objects in SOC. (f) Distribution of instance sizes in the SOCand ILSO datasets. (g) Visual examples of attributes. Best view on screen and zoomed-in for details.
Name | SOC-Train | SOC-Val | SOC-Test | Total | Link |
---|---|---|---|---|---|
Salient Object (Sal) | 1,800 | 600 | 600 | 3,000 | |
Non-Salient Object (NonSal) | 1,800 | 600 | 600 | 3,000 | |
Total | 3,600 | 1,200 | 1,200 | 6,000 | Baidu/Google (730.2MB) |
Baidu/Google (441.32MB) | Baidu/Google (146.56MB) | Baidu/Google (141.86MB) |
Object-level Ground-Truth of the SOC Test Set released. Baidu
Instance-level Ground-Truth of the SOC Test Set released. Baidu
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 in 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 new file name COCO_train2014_000000080168.png to prevent some errors during training your model.
Download link: Baidu.
Note that: If the model used S-measure/E-measure will be marked with bold.
Download link: Google.
No. | Name. | Pub. | Year | Title | Links |
---|---|---|---|---|---|
01 | It | TPAMI | 1998 | A Model of Saliency-Based Visual Attention for Rapid Scene Analysis | [Paper]/[Code] |
02 | FG | ACMMM | 2003 | Contrast-based image attention analysis by using fuzzy growing | [Paper]/[Code] |
03 | RSA | ACMMM | 2005 | Robust subspace analysis for detecting visual attention regions in images | [Paper]/[Code] |
04 | AIM | NeurIPS | 2005 | Saliency Based on Information Maximization | [Paper]/[Code] |
05 | RE | ICME | 2006 | Region enhanced scale-invariant saliency detection | [Paper]/[Code] |
06 | SR | CVPR | 2007 | Saliency Detection A Spectral Residual Approach | [Paper]/[Code] |
07 | GB | NeurIPS | 2007 | Graph-Based Visual Saliency | [Paper]/[Code] |
08 | RU | TMM | 2007 | A rule based technique for extraction of visual attention regions based on real-time clustering | [Paper]/[Code] |
09 | SUN | JOV | 2008 | SUN: A bayesian framework for saliency using natural statistics | [Paper]/[Code] |
10 | AC | ICVS | 2008 | Salient region detection and segmentation | [Paper]/[Code] |
11 | FT | CVPR | 2009 | Frequency-tuned Salient Region Detection | [Paper]/[Code] |
12 | ICC | ICCV | 2009 | Image saliency by isocentric curvedness and color | [Paper]/[Code] |
13 | EDS | PR | 2009 | A simple method for detecting salient regions | [Paper]/[Code] |
14 | CA | CVPR | 2010 | Context-Aware Saliency Detection | [Paper]/[Code] |
15 | SEG | ECCV | 2010 | Segmenting Salient Objects from Images and Videos | [Paper]/[Code] |
16 | MSSS | ICIP | 2010 | Saliency Detection using Maximum Symmetric Surround | [Paper]/[Code] |
17 | CSM | ACMMM | 2010 | Automatic interesting object extraction from images using complementary saliency maps | [Paper]/[Code] |
18 | HC,RC | CVPR | 2011 | Global Contrast based Salient Region Detection | [Paper]/[Code] |
19 | SVO | ICCV | 2011 | Fusing generic objectness and visual saliency for salient object detection | [Paper]/[Code] |
20 | CSD | ICCV | 2011 | Center-surround divergence of feature statistics for salient object detection | [Paper]/[Code] |
21 | CC | ICCV | 2011 | Salient object detection using concavity context | [Paper]/[Code] |
22 | CB | BMVC | 2011 | Automatic Salient Object Segmentation Based on Context and Shape Prior | [Paper]/[Code] |
23 | SF | CVPR | 2012 | Saliency Filters Contrast Based Filtering for Salient Region Detection | [Paper]/[Code] |
24 | LR | CVPR | 2012 | A Unified Approach to Salient Object Detection via Low Rank Matrix Recovery | [Paper]/[Code] |
25 | GS | ECCV | 2012 | Geodesic saliency using background priors | [Paper]/[Code] |
26 | BSF | ICIP | 2012 | Saliency Detection Based on Integration of Boundary and Soft-Segmentation | [Paper]/[Code] |
27 | GC,GU | ICCV | 2013 | Efficient Salient Region Detection with Soft Image Abstraction | [Paper]/[Code] |
28 | MR | CVPR | 2013 | Saliency Detection via Graph-Based Manifold Ranking | [Paper]/[Code] |
29 | MC | ICCV | 2013 | Saliency Detection via Absorbing Markov Chain | [Paper]/[Code] |
30 | DRFI | CVPR | 2013 | Salient Object Detection A Discriminative Regional Feature Integration Approach | [Paper]/[Code] |
31 | DSR | ICCV | 2013 | Saliency Detection via Dense and Sparse Reconstruction | [Paper]/[Code] |
32 | PISA | CVPR | 2013 | Pisa: Pixelwise image saliency by aggregating complementary appearance contrast measures with spatial priors | [Paper]/[Code] |
33 | CRF | CVPR | 2013 | Saliency aggregation: A data-driven approach | [Paper]/[Code] |
34 | HS | CVPR | 2013 | Hierarchical Saliency Detection | [Paper]/[Code] |
35 | PCA | CVPR | 2013 | What Makes a Patch Distinct | [Paper]/[Code] |
36 | STD | CVPR | 2013 | Statistical textural distinctiveness for salient region detection in natural images | [Paper]/[Code] |
38 | SUB | CVPR | 2013 | Submodular salient region detection | [Paper]/[Code] |
39 | UFO | ICCV | 2013 | Salient Region Detection by UFO Uniqueness, Focusness and Objectness | [Paper]/[Code] |
40 | CHM | ICCV | 2013 | Contextual hypergraph modeling for salient object detection | [Paper]/[Code] |
41 | COV | JOV | 2013 | Visual saliency estimation by nonlinearly integrating features using region covariances | [Paper]/[Code] |
42 | CIO | ICCV | 2013 | Category-independent object-level saliency detection | [Paper]/[Code] |
43 | GR | SPL | 2013 | Graph-Regularized Saliency Detection With Convex-Hull-Based Center Prior | [Paper]/[Code] |
44 | SLMR | BMVC | 2013 | Segmentation driven lowrank matrix recovery for saliency detection | [Paper]/[Code] |
45 | LSSC | TIP | 2013 | Bayesian Saliency via Low and Mid Level Cues | [Paper]/[Code] |
46 | LSMD | AAAI | 2013 | Salient object detection via low-rank and structured sparse matrix decomposition | [Paper]/[Code] |
47 | HDCT | CVPR | 2014 | Salient Region Detection via High-Dimensional Color Transform | [Paper]/[Code] |
48 | PDE | CVPR | 2014 | Adaptive partial differential equation learning for visual saliency detection | [Paper]/[Code] |
49 | RBD | CVPR | 2014 | Saliency Optimization from Robust Background Detection | [Paper]/[Code] |
50 | MSS | SPL | 2014 | Saliency Detection with Multi-Scale Superpixels | [Paper]/[Code] |
51 | GP | ICCV | 2015 | Generic Promotion of Diffusion-Based Salient Object Detection | [Paper]/[Code] |
52 | MBS | ICCV | 2015 | Minimum Barrier Salient Object Detection at 80 FPS | [Paper]/[Code] |
53 | WSC | CVPR | 2015 | A Weighted Sparse Coding Framework for Saliency Detection | [Paper]/[Code] |
54 | RRW | CVPR | 2015 | Robust saliency detection via regularized random walks ranking | [Paper]/[Code] |
55 | TLLT | CVPR | 2015 | Saliency Propagation from Simple to Difficult | [Paper]/[Code] |
56 | BL | CVPR | 2015 | Salient Object Detection via Bootstrap Learning | [Paper]/[Code] |
57 | BSCA | CVPR | 2015 | Saliency Detection via Cellular Automata | [Paper]/[Code] |
58 | GLC | PR | 2015 | Salient Object Detection via Global and Local Cues | [Paper]/[Code] |
59 | LPS | TIP | 2015 | Inner and Inter Label Propagation Salient Object Detection in the Wild | [Paper]/[Code] |
60 | MAPM | TIP | 2015 | Saliency Region Detection based on Markov Absorption Probabilities | [Paper]/[Code] |
61 | NCS | TIP | 2015 | Normalized cut-based saliency detection by adaptive multi-level region merging | [Paper]/[Code] |
62 | BFS | NC | 2015 | Saliency Detection via Background and Foreground Seed Selection | [Paper]/[Code] |
63 | UF | TMM | 2016 | A Universal Framework for Salient Object Detection | [Paper]/[Code] |
64 | MST | CVPR | 2016 | Real-Time Salient Object Detection with a Minimum Spanning Tree | [Paper]/[Code] |
65 | PM | ECCV | 2016 | Pattern Mining Saliency | [Paper]/[Code] |
66 | DSP | PR | 2016 | Discriminative saliency propagation with sink points | [Paper]/[Code] |
67 | EBM | IJCAI | 2016 | Saliency Transfer: An Example-Based Method for Salient Object Detection | [Paper]/[Code] |
68 | AWC | Neurocomputing | 2016 | Robust manifold-preserving diffusion-based saliency detection by adaptive weight construction | [Paper]/[Code] |
69 | MRMF | TNNLS | 2016 | Manifold Ranking-Based Matrix Factorization for Saliency Detection | [Paper]/[Code] |
70 | SBCRF | Neurocomputing | 2017 | A superpixel-based CRF saliency detection approach | [Paper]/[Code] |
71 | WLRR | SPL | 2017 | Salient Object Detection via Weighted Low Rank Matrix Recovery | [Paper]/[Code] |
72 | MIL | TIP | 2017 | Salient Object Detection via Multiple Instance Learning | [Paper]/[Code] |
73 | SMD | PAMI | 2017 | Salient Object Detection via Structured Matrix Decomposition | [Paper]/[Code] |
74 | MDC | TIP | 2017 | 300-FPS Salient Object Detection via Minimum Directional Contrast | [Paper]/[Code] |
75 | SS | NC | 2017 | Spectral Salient Object Detection | [Paper]/[Code] |
76 | IFC | TMM | 2017 | Iterative Feedback Control Based Salient Object Segmentation | [Paper]/[Code] |
77 | CCRF | TMM | 2017 | Saliency Detection by Fully Learning A Continuous Conditional Random Field | [Paper]/[Code] |
78 | ELER | CVPR | 2017 | What is and what is not a salient object? learning salient object detector by ensembling linear exemplar regressors | [Paper]/[Code] |
79 | DIMD | PR | 2017 | Diversity Induced Matrix Decomposition Model for salient object detection | [Paper]/[Code] |
80 | ProS | NC | 2018 | Salient Object Detection via Proposal Selection | [Paper]/[Code] |
81 | WMR | NC | 2018 | Saliency detection via affinity graph learning and weighted manifold ranking | [Paper]/[Code] |
82 | RCRR | TIP | 2018 | Reversion correction and regularized random walk ranking for saliency detection | [Paper]/[Code] |
83 | JLSE | TIP | 2018 | Exemplar-aided Salient Object Detection via Joint Latent Space Embedding | [Paper]/[Code] |
84 | WFD | PR | 2018 | Water flow driven salient object detection at 180 fps | [Paper]/[Code] |
85 | FBQ | Access | 2018 | Hypergraph Optimization for Salient Region Detection Based on Foreground and Background Queries | [Paper]/[Code] |
86 | FTOE | TMM | 2019 | Salient Object Detection via Fuzzy Theory and Object-level Enhancement | [Paper]/[Code] |
87 | KSR | TIP | 2019 | Visual Saliency Detection via Kernelized Subspace Ranking with Active Learning | [Paper]/[Code] |
88 | FCB | TIP | 2019 | Exploiting Color Volume and Color Difference for Salient Region Detection | [Paper]/[Code] |
89 | TSG | TCSVT | 2019 | Salient Object Detection Via Two-Stage Graphs | [Paper]/[Code] |
90 | DSC | TCSVT | 2019 | Direction Selective Contour Detection for Salient Objects | [Paper]/[Code] |
91 | AIGC | TCSVT | 2019 | Adaptive Irregular Graph Construction Based Salient Object Detection | [Paper]/[Code] |
92 | NIO | TNNLS | 2019 | Semisupervised Learning Based on a Novel Iterative Optimization Model for Saliency Detection | [Paper]/[Code] |
93 | MSR | TIP | 2019 | 50 FPS Object-Level Saliency Detection via Maximally Stable Region | [Paper]/[Code] |
94 | MSGC | TMM | 2019 | Saliency Detection via Multi-Scale Global Cues | [Paper]/[Code] |
95 | LRR | TIP | 2019 | Local Regression Ranking for Saliency Detection | [Paper]/[Code] |
Download link: Google.
No. | Name. | Pub. | Year | Title | Links |
---|---|---|---|---|---|
01 | SuperCNN | IJCV | 2015 | A superpixelwise convolutional neural network for salient object detection | Paper/[Code] |
02 | LEGS | CVPR | 2015 | Deep networks for saliency detection via local estimation and global search | Paper/Code |
03 | MC | CVPR | 2015 | Saliency detection by multi-context deep learning | Paper/[Code] |
04 | MDF | CVPR | 2015 | Visual saliency based on multiscale deep features | Paper/[Code] |
05 | DISC | TNNLS | 2016 | DISC: Deep image saliency computing via progressive representation learning | Paper/[Code] |
06 | DSL | TCSVT | 2016 | Dense and Sparse Labeling with Multi-Dimensional Features for Saliency Detection | Paper/[Code] |
07 | DS | TIP | 2016 | DeepSaliency: Multi-task deep neural network model for salient object detection | Paper/[Code] |
08 | SSD | ECCV | 2016 | A shape-based approach for salient object detection using deep learning | Paper/[Code] |
09 | CRPSD | ECCV | 2016 | Saliency Detection via Combining Region-Level and Pixel-Level Predictions with CNNs | Paper/[Code] |
10 | RFCN | ECCV | 2016 | Saliency detection with recurrent fully convolutional networks | Paper/Code |
11 | RFCN | TPAMI | 2019 | Salient object detection with recurrent fully convolutional networks | Paper/[Code] |
12 | MAP | CVPR | 2016 | Unconstrained salient object detection via proposal subset optimization | Paper/[Code] |
13 | SU | CVPR | 2016 | Saliency unified: A deep architecture for simultaneous eye fixation prediction and salient object segmentation | Paper/[Code] |
14 | RACDNN | CVPR | 2016 | Recurrent attentional networks for saliency detection | Paper/[Code] |
15 | ELD | CVPR | 2016 | Deep Saliency with Encoded Low level Distance Map and High Level Features | Paper/Code |
16 | DHS | CVPR | 2016 | DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection | Paper/Code |
17 | DCL | CVPR | 2016 | Deep Contrast Learning for Salient Object Detection | Paper/[Code] |
18 | DSRCNN | ACMMM | 2016 | Deeply-Supervised Recurrent Convolutional Neural Network for Saliency Detection | Paper/[Code] |
19 | MSCNet | ACMMM | 2017 | Multi-Scale Cascade Network for Salient Object Detection | Paper/[Code] |
20 | CAR | BMVC | 2017 | Salient object detection using a context-aware refinement network | Paper/[Code] |
21 | DLS | CVPR | 2017 | Deep Level Sets for Salient Object Detection | Paper/[Code] |
22 | MSRNet | CVPR | 2017 | Instance-Level Salient Object Segmentation | Paper/Code |
23 | WSS | CVPR | 2017 | Learning to Detect Salient Objects with Image-level Supervision | Paper/Code |
24 | SRM | ICCV | 2017 | A stagewise refinement model for detecting salient objects in images | Paper/Code |
25 | NLDF | CVPR | 2017 | Non-Local Deep Features for Salient Object Detection | Paper/Code |
26 | DSS | CVPR/TPAMI | 2017/2019 | Deeply Supervised Salient Object Detection with Short Connections | Paper/Code |
27 | SalGAN | CVPR | 2017 | SalGAN: visual saliency prediction with adversarial networks | Paper/Code |
28 | FSN | ICCV | 2017 | Look, perceive and segment: Finding the salient objects in images via two-stream fixation-semantic cnns | Paper/[Code] |
29 | DSOS | ICCV | 2017 | Delving into Salient Object Subitizing and Detection | Paper/[Code] |
30 | SVF | ICCV | 2017 | Supervision by Fusion: Towards Unsupervised Learning of Deep Salient Object Detector | Paper/Code |
31 | UCF | ICCV | 2017 | Learning Uncertain Convolutional Features for Accurate Saliency Detection | Paper/Code |
32 | AMU | ICCV | 2017 | Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection | Paper/Code |
33 | UGA | TIP | 2018 | An Unsupervised Game-Theoretic Approach to Saliency Detection | Paper/Code |
34 | Refinet | TMM | 2018 | Refinet A deep segmentation assisted refinement network for salient object detection | Paper/Results (psw: iziq) |
35 | MSED | Neurocomputing | 2018 | Multi-scale deep encoder-decoder network for salient object detection | Paper/[Code] |
36 | EARNet | T-Cybernetics | 2018 | Embedding Attention and Residual Network for Accurate Salient Object Detection | Paper/[Code] |
37 | LFCS | T-Cybernetics | 2018 | Semi-Supervised Salient Object Detection Using a Linear Feedback Control System Model | Paper/[Code] |
38 | LICNN | AAAI | 2018 | Lateral inhibition-inspired convolutional neural network for visual attention and saliency detection | Paper/[Code] |
39 | ASMO | AAAI | 2018 | Weakly supervised salient object detection using image labels | Paper/[Code] |
40 | RADF | AAAI | 2018 | Recurrently aggregating deep features for salient object detection | Paper/[Code] |
41 | R3Net | IJCAI | 2018 | R3net: Recurrent residual refinement network for saliency detection | Paper/[Code] |
42 | LFR | IJCAI | 2018 | Salient Object Detection by Lossless Feature Reflection | Paper/Code |
43 | C2SNet | ECCV | 2018 | Contour Knowledge Transfer for Salient Object Detection | Paper/Code |
44 | RAS | ECCV | 2018 | Reverse Attention for Salient Object Detection | Paper/Code |
45 | LPSNet | CVPR | 2018 | Learning to promote saliency detectors | Paper/Code |
46 | RSDNet | CVPR | 2018 | Revisiting salient object detection: Simultaneous detection, ranking, and subitizing of multiple salient objects | Paper/Code |
47 | DUS | CVPR | 2018 | Deep unsupervised saliency detection: A multiple noisy labeling perspective | Paper/Code |
48 | ASNet | CVPR | 2018 | Salient Object Detection Driven by Fixation Prediction | Paper/Code |
49 | ASNet | TPAMI | 2019 | Inferring Salient Objects from Human Fixations | Paper/Code |
50 | BDMPM | CVPR | 2018 | A Bi-Directional Message Passing Model for Salient Object Detection | Paper/Code |
51 | DGRL | CVPR | 2018 | Detect Globally, Refine Locally: A Novel Approach to Saliency Detection | Paper/Code |
52 | PiCANet | CVPR | 2018 | PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection | Paper/Code |
53 | PAGR | CVPR | 2018 | Progressive Attention Guided Recurrent Network for Salient Object Detection | Paper/Code |
54 | DANet | JSTSP | 2019 | Distortion-adaptive Salient Object Detection in 360∘ Omnidirectional Images | Paper/[Code] |
55 | RSR | TPAMI | 2019 | Relative Saliency and Ranking: Models, Metrics, Data and Benchmarks | Paper/[Code] |
56 | Hyperfusion-Net | PR | 2019 | Hyperfusion-Net: Hyper-densely reflective feature fusion for salient object detection | Paper/[Code] |
57 | Deepside | Neurocomputing | 2019 | Deepside: A General Deep Framework for Salient Object Detection | Paper/[Code] |
58 | LVNet | TGRS | 2019 | Nested Network with Two-Stream Pyramid for Salient Object Detection in Optical Remote Sensing Images | Paper/[Code] |
59 | LFRWS | TIP | 2019 | Salient Object Detection with Lossless Feature Reflection and Weighted Structural Loss | Paper/[Code] |
60 | FBG | TIP | 2019 | Focal Boundary Guided Salient Object Detection | Paper/[Code] |
61 | ConnNet | TIP | 2019 | ConnNet: A long-range relation-aware pixel-connectivity network for salient segmentation | Paper/[Code] |
62 | CIG | TIP | 2019 | Deep Salient Object Detection with Contextual Information Guidance | Paper/[Code] |
63 | SPA | TIP | 2019 | Semantic Prior Analysis for Salient Object Detection | Paper/[Code] |
64 | CDMG | TIP | 2019 | Weakly Supervised Salient Object Detection by Learning A Classifier-Driven Map Generator | Paper/[Code] |
65 | CCAL | TMM | 2019 | Salient Object Detectioin Using Cascaded Convolutional Neural Networks and Adversarial Learning | Paper/[Code] |
66 | SIA | TMM | 2019 | Saliency Integration An Arbitrator Model | Paper/[Code] |
67 | MIJR | TCSVT | 2019 | Salient Object Detection via Multiple Instance Joint Re-Learning | Paper/[Code] |
68 | AADF | TCSVT | 2019 | Aggregating Attentional Dilated Features for Salient Object | Paper/Code |
69 | ROSA | T-Cybernetics | 2019 | ROSA: Robust Salient Object Detection against Adversarial Attacks | Paper/Code |
70 | SSNet | TPAMI | 2019 | Synthesizing Supervision for Learning Deep Saliency Network without Human Annotation | Paper/[Code] |
71 | DEF | AAAI | 2019 | Deep Embedding Features for Salient Object Detection | Paper/Code |
72 | SuperVAE | AAAI | 2019 | Supervae: Superpixelwise variational autoencoder for salient object detection | Paper/[Code] |
73 | CapSal | CVPR | 2019 | CapSal: Leveraging Captioning to Boost Semantics for Salient Object Detection | Paper/Code |
74 | BASNet | CVPR | 2019 | BASNet: Boundary Aware Salient Object Detection | Paper/Code |
75 | PFANet | CVPR | 2019 | Pyramid Feature Attention Network for Saliency detection | Paper/Code |
76 | MWS | CVPR | 2019 | Multi-source weak supervision for saliency detection | Paper/Code |
77 | ICNet | CVPR | 2019 | An Iterative and Cooperative Top-down and Bottom-up Inference Network for Salient Object Detection | Paper/Code |
78 | PAGE-Net | CVPR | 2019 | Salient Object Detection With Pyramid Attention and Salient Edges | Paper/Code |
79 | CPD | CVPR | 2019 | Cascaded Partial Decoder for Accurate and Fast Salient Object Detection | Paper/Code |
80 | MLMSNet | CVPR | 2019 | A Mutual Learning Method for Salient Object Detection with intertwined Multi-Supervision | Paper/Code |
81 | AFNet | CVPR | 2019 | Attentive Feedback Network for Boundary-aware Salient Object Detection | Paper/Code |
82 | DPOR | ICCV | 2019 | Employing Deep Part-Object Relationships for Salient Object Detection | Paper/Code |
83 | SIBA | ICCV | 2019 | Selectivity or Invariance: Boundary-aware Salient Object Detection | Paper/Code |
84 | JDF | ICCV | 2019 | Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection | Paper/Code |
85 | FLoss | ICCV | 2019 | Optimizing the F-measure for Threshold-free Salient Object Detection | Paper/Code |
86 | HRSOD | ICCV | 2019 | Towards High-Resolution Salient Object Detection | Paper/Code |
87 | EGNet | ICCV | 2019 | EGNet: Edge Guidance Network for Salient Object Detection | Paper/Code |
88 | SCRN | ICCV | 2019 | Stacked Cross Refinement Network for Salient Object Detection | Paper/Code |
89 | PoolNet | ICCV | 2019 | A Simple Pooling-Based Design for Real-Time Salient Object Detection | Paper/Code |
90 | DeepUSPS | NeurIPS | 2019 | Deep Robust Unsupervised Saliency Prediction With Self-Supervision | Paper/Code |
91 | EAI | ICLR | 2019 | Efficient Saliency Maps for Explainable AI | Paper/[Code] |
92 | DFI | TIP | 2020 | Dynamic Feature Integration for Simultaneous Detection of Salient Object, Edge and Skeleton | Paper/Code |
93 | CALoss | TIP | 2020 | Contour-aware loss: Boundary-aware learning for salient object segmentation | Paper/[Code] |
94 | EGNL | TCSVT | 2020 | Edge-guided non-local fully convolutional network for salient object detection | Paper/[Code] |
95 | CAGNet | PR | 2020 | CAGNet: Content-aware guidance for salient object detection | Paper/Code |
96 | FastSaliency | T-Cybernetics | 2020 | Lightweight Salient Object Detection via Hierarchical Visual Perception Learning | Paper/Code |
97 | PFPNet | AAAI | 2020 | Progressive Feature Polishing Network for Salient Object Detection | Paper/Code |
98 | F3Net | AAAI | 2020 | F3Net: Fusion, Feedback and Focus for Salient Object Detection | Paper/Code |
99 | GCPANet | AAAI | 2020 | Global Context-Aware Progressive Aggregation Network for Salient Object Detection | Paper/Code |
100 | ADASOD | AAAI | 2020 | Multi-spectral Salient Object Detection by Adversarial Domain Adaptation | Paper/Code |
101 | MTSA | AAAI | 2020 | Multi-Type Self-Attention Guided Degraded Saliency Detection | Paper/Code |
102 | ScrSOD | CVPR | 2020 | Weakly-Supervised Salient Object Detection via Scribble Annotations | Paper/Code |
103 | MINet | CVPR | 2020 | Multi-scale Interactive Network for Salient Object Detection | Paper/Code |
104 | ITSD | CVPR | 2020 | Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection | Paper/Code |
105 | LDF | CVPR | 2020 | Label Decoupling Framework for Salient Object Detection | Paper/Code |
106 | Sal100K | ECCV | 2020 | Highly Efficient Salient Object Detection with 100K Parameters | Paper/Code |
107 | NSOD | ECCV | 2020 | n-Reference Transfer Learning for Saliency Prediction | Paper/Code |
108 | ABP-Saliency | ECCV | 2020 | Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection | Paper/Code |
109 | GateNet | ECCV | 2020 | Suppress and Balance: A Simple Gated Network for Salient Object Detection | Paper/Code |
110 | FewCSOD | NeurIPS | 2020 | Few-Cost Salient Object Detection with Adversarial-Paced Learning | Paper/Code |
111 | DNA | T-Cybernetics | 2021 | DNA: Deeply supervised nonlinear aggregation for salient object detection | Paper/Code |
112 | DAFNet | TIP | 2021 | Dense Attention Fluid Network for Salient Object Detection in Optical Remote Sensing Images | Paper/Code |
113 | WSSOS | TCSVT | 2021 | Weakly-Supervised Saliency Detection via Salient Object Subitizing | Paper/Code |
114 | DACNet | TMM | 2021 | Dense Attention-guided Cascaded Network for Salient Object Detection of Strip Steel Surface Defects | Paper/Code |
115 | DCN | TIP | 2021 | Decomposition and Completion Network for Salient Object Detection | Paper/Code |
116 | PurNet | TIP | 2021 | Salient Object Detection with Purificatory Mechanism and Structural Similarity Loss | Paper/Code |
117 | PSGLoss | TIP | 2021 | Progressive Self-Guided Loss for Salient Object Detection | Paper/Code |
118 | SAMNet | TIP | 2021 | SAMNet: Stereoscopically Attentive Multi-scale Network for Lightweight Salient Object Detection | Paper/Code |
119 | LSC | AAAI | 2021 | Structure-Consistent Weakly Supervised Salient Object Detection with Local Saliency Coherence | Paper/Code |
120 | PFSNet | AAAI | 2021 | Pyramidal Feature Shrinking for Salient Object Detection | Paper/Code |
121 | LGSL | AAAI | 2021 | Locate Globally, Segment Locally: A Progressive Architecture with Knowledge Review Network for Salient Object Detection | Paper/Code |
122 | RATM | AAAI | 2021 | Generating Diversified Comments via Reader-Aware Topic Modeling and Saliency Detection | Paper/Code |
123 | MeshSaliency | CVPR | 2021 | Mesh Saliency: An Independent Perceptual Measure or A Derivative of Image Saliency? | Paper/Code |
124 | BBESOD | CVPR | 2021 | Black-Box Explanation of Object Detectors via Saliency Maps | Paper/Code |
125 | CAMERAS | CVPR | 2021 | CAMERAS: Enhanced Resolution and Sanity Preserving Class Activation Mapping for Image Saliency | Paper/Code |
126 | SGIT | CVPR | 2021 | Saliency-Guided Image Translation | Paper/Code |
127 | Auto-MSFNet | ACMMM | 2021 | Auto-MSFNet: Search Multi-scale Fusion Network for Salient Object Detection | Paper/Code |
128 | CTDNet | ACMMM | 2021 | Complementary Trilateral Decoder for Fast and Accurate Salient Object Detection | Paper/Code |
129 | VST | ICCV | 2021 | Visual Saliency Transformer | Paper/Code |
130 | HQSOD | ICCV | 2021 | Disentangled High Quality Salient Object Detection | Paper/Code |
131 | iNAS | ICCV | 2021 | iNAS: Integral NAS for Device-Aware Salient Object Detection | Paper/Code |
132 | SCASOD | ICCV | 2021 | Scene Context-Aware Salient Object Detection | Paper/Code |
133 | MFNet | ICCV | 2021 | MFNet: Multi-Filter Directive Network for Weakly Supervised Salient Object Detection | Paper/Code |
134 | SOR | ICCV | 2021 | Salient Object Ranking with Position-Preserved Attention | Paper/Code |
135 | EGVT | NeurIPS | 2021 | Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction | Paper/Code |
136 | Reg-GNN | NeurIPS | 2021 | Discovering Dynamic Salient Regions for Spatio-Temporal Graph Neural Networks | Paper/Code |
137 | UDASOD | AAAI | 2022 | Unsupervised Domain Adaptive Salient Object Detection Through Uncertainty-Aware Pseudo-Label Learning | Paper/Code |
138 | CDF | AAAI | 2022 | A Causal Debiasing Framework for Unsupervised Salient Object Detection | Paper/Code |
139 | SalCoopNets | AAAI | 2022 | Energy-Based Generative Cooperative Saliency Prediction | Paper/Code |
140 | PSSOD | AAAI | 2022 | Weakly-Supervised Salient Object Detection Using Point Supervison | Paper/Code |
141 | TRACER | AAAI | 2022 | TRACER: Extreme Attention Guided Salient Object Tracing Network | Paper/Code |
142 | PoolNet+ | TPAMI | 2022 | PoolNet+: Exploring the Potential of Pooling for Salient Object Detection | Paper/Code |
143 | SOD100K | TPAMI | 2022 | A Highly Efficient Model to Study the Semantics of Salient Object Detection | Paper/Code |
144 | CorrNet | TGRS | 2022 | Lightweight Salient Object Detection in Optical Remote Sensing Images via Feature Correlation | Paper/Code |
145 | CDBF | TOMM | 2022 | Disentangle Saliency Detection into Cascaded Detail Modeling and Body Filling | Paper/Code |
146 | NSALWSS | TMM | 2022 | Noise-Sensitive Adversarial Learning for Weakly Supervised Salient Object Detection | Paper/Code |
147 | ACCoNet | T-Cybernetics | 2022 | Adjacent Context Coordination Network for Salient Object Detection in Optical Remote Sensing Images | Paper/Code |
148 | ICON | TPAMI-Minor | 2022 | Salient Object Detection via Integrity Learning | Paper/Code |
149 | SOC-DataAug | TPAMI | 2022 | Salient objects in clutter | Paper/Code |
150 | BAS | arXiv | 2022 | Boundary-aware segmentation network for mobile and web applications | Paper/Code |
151 | SHNet | ECCV | 2022 | Saliency Hierarchy Modeling via Generative Kernels for Salient Object Detection | Paper |
Download link: Google.
Demo1: https://dengpingfan.github.io/videos/SOD-App-BASNetAR.mp4
Please cite our paper if you use our results:
@article{fan2022salient,
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}
}