显著性目标检测代码全汇总！(包含2D、3D、4D以及Video)

转载于极市开发者原创投稿https://mp.weixin.qq.com/s/ZSytEsVSjBU_zjy5YPxPeA

这里是加以翻译

SOD CNNs-based Read List

在这个知识库中，我们主要关注基于深度学习的显著性方法(2D RGB, 3D RGB-D, Video SOD and 4D Light Field) ，并提供总结(Code and Paper).。我们希望这份回购能帮助大家更好地理解深度学习时代的显著性检测。 评估指标。

❗ 2D SOD: Add five papesr ECCV20
❗ 3D SOD: Add nine papers ECCV20 and two ACMM20 papers
❗ Video SOD : Add three papers ECCV20, Continuously Updating!

🏃 We will keep updating it. 🏃

Content:

  1. An overview of the Paper List
  2. 2D RGB Saliency Detection
  3. 3D RGB Saliency Detection
  4. 4D Light Field Saliency Detection
  5. Video Saliency Detection
  6. Survery and earlier Methods
  7. The SOD dataset download
  8. Evaluation Metrics

Overall

avatar

2D RGB Saliency Detection

2020

No. Pub. Title Links
01 AAAI Progressive Feature Polishing Network for Salient Object Detection Paper/Code
02 AAAI Global Context-Aware Progressive Aggregation Network for Salient Object Detection Paper/Code
03 AAAI F3Net: Fusion, Feedback and Focus for Salient Object Detection Paper/Code
04 AAAI Multi-spectral Salient Object Detection by Adversarial Domain Adaptation Paper/Code
05 AAAI Multi-Type Self-Attention Guided Degraded Saliency Detection Paper/Code
06 CVPR Weakly-Supervised Salient Object Detection via Scribble Annotations Paper/Code
07 CVPR Taking a Deeper Look at the Co-salient Object Detection Paper/Code
08 CVPR Multi-scale Interactive Network for Salient Object Detection Paper/Code
09 CVPR Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection Paper/Code
10 CVPR Label Decoupling Framework for Salient Object Detection Paper/Code
11 CVPR Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection Paper/Code
🚩 12 ECCV Highly Efficient Salient Object Detection with 100K Parameters Paper/Code
🚩 13 ECCV n-Reference Transfer Learning for Saliency Prediction Paper/Code
🚩 14 ECCV Gradient-Induced Co-Saliency Detection Paper/Code
🚩 13 ECCV Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection Paper/Code
🚩 15 ECCV Suppress and Balance: A Simple Gated Network for Salient Object Detection Paper/Code

2019

No. Pub. Title Links
01 CVPR AFNet: Attentive Feedback Network for Boundary-aware Salient Object Detection Paper/Code
02 CVPR BASNet: Boundary Aware Salient Object Detection Paper/Code
03 CVPR CPD: Cascaded Partial Decoder for Accurate and Fast Salient Object Detection Paper/Code
04 CVPR Multi-source weak supervision for saliency detection Paper/Code
05 CVPR MLMSNet:A Mutual Learning Method for Salient Object Detection with intertwined Multi-Supervision Paper/Code
06 CVPR CapSal: Leveraging Captioning to Boost Semantics for Salient Object Detection Paper/Code
07 CVPR PoolNet: A Simple Pooling-Based Design for Real-Time Salient Object Detection Paper/Code
08 CVPR An Iterative and Cooperative Top-down and Bottom-up Inference Network for Salient Object Detection Paper/Code
09 CVPR Pyramid Feature Attention Network for Saliency detection Paper/Code
10 AAAI Deep Embedding Features for Salient Object Detection Paper/Code
11 ICIP Salient Object Detection Via Deep Hierarchical Context Aggregation And Multi-Layer Supervision Paper/Code
12 IEEE TCSVT AADF-Net: Aggregating Attentional Dilated Features for Salient Object Paper/Code
13 IEEE TCyb ROSA: Robust Salient Object Detection against Adversarial Attacks Paper/Code
14 arXiv DSAL-GAN: DENOISING BASED SALIENCY PREDICTION WITH GENERATIVE ADVERSARIAL NETWORKS Paper/Code
15 arXiv SAC-Net: Spatial Attenuation Context for Salient Object Detection Paper/Code
16 arXiv SE2Net: Siamese Edge-Enhancement Network for Salient Object Detection Paper/Code
17 arXiv Region Refinement Network for Salient Object Detection Paper/Code
18 arXiv Contour Loss: Boundary-Aware Learning for Salient Object Segmentation Paper/Code
19 arXiv OGNet: Salient Object Detection with Output-guided Attention Module Paper/Code
20 arXiv Edge-guided Non-local Fully Convolutional Network for Salient Object Detection Paper/Code
21 ICCV FLoss:Optimizing the F-measure for Threshold-free Salient Object Detection Paper/Code
22 ICCV Stacked Cross Refinement Network for Salient Object Detection Paper/Code
23 ICCV Selectivity or Invariance: Boundary-aware Salient Object Detection Paper/Code
24 ICCV HRSOD:Towards High-Resolution Salient Object Detection Paper/Code
25 ICCV EGNet:Edge Guidance Network for Salient Object Detection Paper/Code
26 ICCV Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection Paper/Code
27 ICCV Employing Deep Part-Object Relationships for Salient Object Detection Paper/Code
28 NeurIPS Deep Robust Unsupervised Saliency Prediction With Self-Supervision Paper/Code

2018

No. Pub. Title Links
01 CVPR A Bi-Directional Message Passing Model for Salient Object Detection Paper/Code
02 CVPR PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection Paper/Code
03 CVPR PAGR: Progressive Attention Guided Recurrent Network for Salient Object Detection Paper/Code
04 CVPR Learning to promote saliency detectors Paper/Code
05 CVPR Detect Globally, Refine Locally: A Novel Approach to Saliency Detection Paper/Code
06 CVPR Salient Object Detection Driven by Fixation Prediction Paper/Code
07 IJCAI R3Net: Recurrent Residual Refinement Network for Saliency Detection Paper/Code
08 IJCAI LFR: Salient Object Detection by Lossless Feature Reflection Paper/Code
09 ECCV Contour Knowledge Transfer for Salient Object Detection Paper/Code
10 ECCV Reverse Attention for Salient Object Detection Paper/Code
11 IEEE TIP An unsupervised game-theoretic approach to saliency detection Paper/Code
12 arXiv Agile Amulet: Real-Time Salient Object Detection with Contextual Attention Paper/Code
13 arXiv HyperFusion-Net: Densely Reflective Fusion for Salient Object Detection Paper/Code
14 arXiv (TBOS)Three Birds One Stone: A Unified Framework for Salient Object Segmentation, Edge Detection and Skeleton Extraction Paper/Code

2017

No. Pub. Title Links
01 CVPR DSS: Deeply Supervised Salient Object Detection with Short Connections Paper/Code
02 CVPR Non-Local Deep Features for Salient Object Detection Paper/Code
03 CVPR Learning to Detect Salient Objects with Image-level Supervision Paper/Code
04 CVPR SalGAN: visual saliency prediction with adversarial networks Paper/Code
05 ICCV A Stagewise Refinement Model for Detecting Salient Objects in Images Paper/Code
06 ICCV Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection Paper/Code
07 ICCV Learning Uncertain Convolutional Features for Accurate Saliency Detection Paper/Code

2016

No. Pub. Title Links
01 CVPR DHSNet: Deep hierarchical saliency network for salient object detection Paper/Code
02 CVPR ELD: Deep Saliency with Encoded Low level Distance Map and High Level Features Paper/Code
03 ECCV RFCN: Saliency detection with recurrent fully convolutional networks Paper/Code

3D RGB-D Saliency Detection

2020

No. Pub. Title Links
01 IEEE TIP ICNet: Information Conversion Network for RGB-D Based Salient Object Detection Paper/Code
02 CVPR JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection Paper/Code
03 CVPR UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders Paper/Code
04 CVPR A2dele: Adaptive and Attentive Depth Distiller for Efficient RGB-D Salient Object Detection Paper/Code
05 CVPR Select, Supplement and Focus for RGB-D Saliency Detection Paper/Code
06 CVPR Learning Selective Self-Mutual Attention for RGB-D Saliency Detection Paper/Code
🚩 07 ECCV Accurate RGB-D Salient Object Detection via Collaborative Learning Paper/Code
🚩 08 ECCV Cross-Modal Weighting Network for RGB-D Salient Object Detection Paper/Code
🚩 09 ECCV BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network Paper/Code
🚩 10 ECCV Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detection Paper/Code
🚩 11 ECCV Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection Paper/Code
🚩 12 ECCV RGB-D Salient Object Detection with Cross-Modality Modulation and Selection Paper/Code
🚩 13 ECCV Cascade Graph Neural Networks for RGB-D Salient Object Detection Paper/Code
🚩 14 ECCV A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection Paper/Code
🚩 15 ECCV Asymmetric Two-Stream Architecture for Accurate RGB-D Saliency Detection Paper/Code
🚩 16 ACMM Is Depth Really Necessary for Salient Object Detection? Paper/Code
🚩 17 ACMM A Top-down and Adaptive Fusion Network for RGB-D Salient Object Detection Paper/Code

2019

No. Pub. Title Links
01 ICCV DMRA: Depth-induced Multi-scale Recurrent Attention Network for Saliency Detection Paper/Code
02 CVPR CPFP: Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection Paper/Code
03 IEEE TIP Three-stream Attention-aware Network for RGB-D Salient Object Detection Paper/Code
04 IEEE PR Multi-modal fusion network with multi-scale multi-path and cross-modal interactions for RGB-D salient object detection Paper/Code
05 arXiv AFNet: Adaptive Fusion for RGB-D Salient Object Detection Paper/Code
06 IEEE TNNLS D3Net:Rethinking RGB-D Salient Object Detection: Models, Datasets, and Large-Scale Benchmarks Paper/Code
07 arXiv CNN-based RGB-D Salient Object Detection: Learn, Select and Fuse Paper/Code

2018

No. Pub. Title Links
01 CVPR PCA: Progressively Complementarity-aware Fusion Network for RGB-D Salient Object Detection Paper/Code
02 IEEE TIP Co-saliency detection for RGBD images based on multi-constraint feature matching and cross label propagation Paper/Code
03 ICME PDNet: Prior-Model Guided Depth-enhanced Network for Salient Object Detection Paper/Code

2017

No. Pub. Title Links
01 ICCV Learning RGB-D Salient Object Detection using background enclosure, depth contrast, and top-down features Paper/Code
02 IEEE TIP DF: RGBD Salient Object Detection via Deep Fusion Paper/Code
03 IEEE TCyb CTMF: Cnns-based rgb-d saliency detection via cross-view transfer and multiview fusion Paper/Code

Traditional methods

No. Pub. Title Links
01 MTA RGBD co-saliency detection via multiple kernel boosting and fusion Paper/Code
02 ICCV17 An Innovative Salient Object Detection Using Center-Dark Channel Prior Paper/Code
03 IEEE SPL Saliency detection for stereoscopic images based on depth confidence analysis and multiple cues fusion Paper/Code
04 IEEE SPL RGBD Co-saliency Detection via Bagging-Based Clustering Paper/Code
05 CVPR Exploiting Global Priors for RGB-D Saliency Detection Paper/Code

4D Light Field Saliency Detection

No. Pub. Title Links
01 TOMM MCA: Saliency Detection on Light Field: A Multi-Cue Approach Paper/Code
02 IJCAI DILF: Saliency Detection with a Deeper Investigation of Light Field Paper/Code
03 CVPR WSC: A Weighted Sparse Coding Framework for Saliency Detection Paper/Code
04 IEEE PAMI Saliency Detection on Light-Field Paper/Code
05 ICCV Deep Learning for Light Field Saliency Detection Paper/Code
06 NeurIPS Memory-oriented Decoder for Light Field Salient Object Detection Paper/Code
07 AAAI Exploit and Replace: An Asymmetrical Two-Stream Architecture for Versatile Light Field Saliency Detection Paper/Code

Video Salient Object Detection

2020

No. Pub. Title Links
01 CVPR STAViS: Spatio-Temporal AudioVisual Saliency Network Paper/Code
🚩 02 ECCV Unified Image and Video Saliency Modeling Paper/Code
🚩 03 ECCV Measuring the importance of temporal features in video saliency Paper/Code
🚩 04 ECCV TENet: Triple Excitation Network for Video Salient Object Detection Paper/Code

2019

No. Pub. Title Links
01 ICCV Motion Guided Attention for Video Salient Object Detection Paper/Code
02 ICCV Semi-Supervised Video Salient Object Detection Using Pseudo-Labels Paper/Code
03 ICCV Temporally-Aggregating Spatial Encoder-Decoder Network for Video Saliency Detection Paper/Code
04 ICCV RANet：Ranking attention Network for Fast Video Object Segmentation Paper/Code
05 CVPR Shifting More Attention to Video Salient Objection Detection Paper/Code
06 CVPR Learning Unsupervised Video Object Segmentation through Visual Attention Paper/Code
07 CVPR See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks Paper/Code

2018

No. Pub. Title Links
01 ECCV Pyramid Dilated Deeper CoonvLSTM for Video Salient Object Detection Paper/Code
02 ECCV DeepVS: A Deep Learning Based Video Saliency Prediction Approach Paper/Code
03 CVPR Revisiting Video Saliency: A Large-scale Benchmark and a New Model Paper/Code
04 CVPR Flow Guided Recurrent Neural Encoder for Video Salient Object Detection Paper/Code
05 IEEE TIP Video Salient Object Detection via Fully Convolutional Networks Paper/Code

2017

No. Pub. Title Links
01 IEEE TIP Learning to Detect Video Saliency with HEVC Features Paper/Code

Earlier Methods

No. Pub. Title Links
01 IEEE TIP15 Salient object detection: A benchmark Paper/Code
02 IEEE TCSVT18 Review of visual saliency detectionwith comprehensive information Paper/Code
03 ACM TIST18 A review of co-saliency detection algorithms: Fundamentals, applications, and challenges Paper/Code
04 IEEE TSP18 Advanced deep-learning techniques for salient and category-specific object detection: A survey Paper/Code
05 IJCV18 Attentive systems: A survey Paper/Project
06 ECCV18 Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground Paper/Code
07 CVM18 Salient object detection: A survey Paper/Code
08 IEEE TNNLS19 Salient Object detection with deep learning: Areview Paper/Code
09 arXiv19 Salient Object Detection in the Deep Learning Era-An In-Depth Survey Paper/Code
10 GitHub20 RGB-D Salient Object Detection: A Survey Paper/Code

The part of the collection is thanks to Deng-Ping Fan and Tao Zhou.

  • Salient Object Detection in the Deep Learning Era: An In-Depth Survey. paper link.
  • This is a paper list published by another author. here
  • RGB-D Salient Object Detection: A Survey. project link.

与最先进的比较

  • Here 包括几乎所有2D显著目标检测算法的性能比较.
  • Here i包括几乎所有3D RGB-D显著目标检测算法的性能比较。

显著性目标检测数据集下载

Evaluation Metrics【评价指标】

  • Saliency maps evaluation.【特征图评价】
    该链接几乎包括用于显著对象检测的所有评估指标，包括E-Measure、S-Measure、F-Measure、MAE Score和PR曲线或BAR指标。 你可以在这里找到 【链接】.

  • Saliency Dataset evaluation.【显著性数据集评估】
    该方法可以在二进制显著性数据集上计算Obj.Area和Obj.Contrast的比值。此工具箱包含两个评估指标，包括obj(Object).Area和obj.Contrast。
    你可以在这里找到【链接】.

AI会议截止日期

Realted AI Conference deadline

Logo
DAMO开发者矩阵

DAMO开发者矩阵，由阿里巴巴达摩院和中国互联网协会联合发起，致力于探讨最前沿的技术趋势与应用成果，搭建高质量的交流与分享平台，推动技术创新与产业应用链接，围绕“人工智能与新型计算”构建开放共享的开发者生态。

更多推荐

cover

RoboTTT：机器人策略的上下文规模化

avatar DAMO开发者矩阵

开题季实测：AI能帮你写报告，但大模型别直接交

开题季自救指南：测了十几款AI工具后，我劝你别再拿通用大模型硬写论文了 开学没几天，后台问"开题报告怎么写"的消息又炸了。 说个真事：我同门上周用某知名大模型生成开题报告，参考文献列了12篇，导师随手一查——7篇搜不到，剩下5篇里有3篇年份和作者对不上。当场被打回，还落了个"学术态度不端"的印象。 这两年AI工具爆发，通用大模型、垂直写作平台、AI智能体满天飞，个个都说自己能写论文。但开题报告这东

avatar DAMO开发者矩阵
cover

EgoEngine：从以自我为中心人类视频到高保真灵巧机器人演示

avatar DAMO开发者矩阵