Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision

RGB Salient Object Detection

3260 papers • 126 benchmarks • 313 datasets

RGB Salient object detection is a task-based on a visual attention mechanism, in which algorithms aim to explore objects or regions more attentive than the surrounding areas on the scene or RGB images. ( Image credit: Attentive Feedback Network for Boundary-Aware Salient Object Detection )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in rgb-salient-object-detection

Trend

Dataset

Best Model

Actions

DUTS-TE

DUTS-TE

DUT-OMRON

DUT-OMRON

ECSSD

ECSSD

Libraries

i

Use these libraries to find rgb-salient-object-detection models and implementations

taozh2017/RGBD-SODsurvey

5 papers 350

Datasets

DUTS

PASCAL-S

HKU-IS

DUT-OMRON

ISTD

ECSSD

SOC

Subtasks

Video Salient Object Detection Dichotomous Image Segmentation Co-Salient Object Detection

Most implemented papers

Res2Net: A New Multi-Scale Backbone Architecture

Philip H. S. Torr, Ming-Ming Cheng, Ming-Hsuan Yang, Shanghua Gao, Kai Zhao, Xinyu Zhang•Mon Apr 01 2019

This paper proposes a novel building block for CNNs, namely Res2Net, by constructing hierarchical residual-like connections within one single residual block that represents multi-scale features at a granular level and increases the range of receptive fields for each network layer.

2898

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

HKU-IS

HKU-IS

PASCAL-S

PASCAL-S

HRSOD

HRSOD

DAVIS-S

DAVIS-S

UHRSD

UHRSD

SBU / SBU-Refine

SBU / SBU-Refine

ISTD

ISTD

UCF

UCF

SOC

SOC

SOD

SOD

3 papers 78

VT5000

SBU / SBU-Refine

SBU / SBU-Refine

HRSOD

0

U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection

Xuebin Qin, Masood Dehghan, Martin Jägersand, Osmar R Zaiane, Chenyang Huang•Sun May 17 2020

A simple yet powerful deep network architecture, U2-Net, for salient object detection (SOD), a two-level nested U-structure that enables us to train a deep network from scratch without using backbones from image classification tasks.

1995 0

RGB-D salient object detection: A survey

Jianbing Shen, Ling Shao, Ming-Ming Cheng, Deng-Ping Fan, Tao Zhou•Fri Jul 31 2020

This paper provides a comprehensive survey of RGB-D based salient object detection models from various perspectives, and review related benchmark datasets in detail, and investigates the ability of existing models to detect salient objects.

283 0

EGNet: Edge Guidance Network for Salient Object Detection

Jiangjiang Liu, Ming-Ming Cheng, Deng-Ping Fan, Jufeng Yang, Jiaxing Zhao, Yang Cao•Wed Aug 21 2019

This paper presents an edge guidance network (EGNet) for salient object detection with three steps to simultaneously model these two kinds of complementary information in a single network to solve the complementarity between salient edge information and salient object information.

1031 0

A Simple Pooling-Based Design for Real-Time Salient Object Detection

Jiashi Feng, Ming-Ming Cheng, Qibin Hou, Jiangjiang Liu, Jianmin Jiang•Sat Apr 20 2019

This work solves the problem of salient object detection by investigating how to expand the role of pooling in convolutional neural networks by building a global guidance module (GGM) and designing a feature aggregation module (FAM) to make the coarse-level semantic information well fused with the fine-level features from the top-down path- way.

960 0

Deeply Supervised Salient Object Detection with Short Connections

Philip H. S. Torr, Z. Tu, Ming-Ming Cheng, A. Borji, Qibin Hou, Xiaowei Hu•Mon Nov 14 2016

This paper proposes a new salient object detection method by introducing short connections to the skip-layer structures within the HED architecture, which takes full advantage of multi-level and multi-scale features extracted from FCNs, providing more advanced representations at each layer, a property that is critically needed to perform segment detection.

1411 0

F3Net: Fusion, Feedback and Focus for Salient Object Detection

Qingming Huang, Junhang Wei, Shuhui Wang•Mon Nov 25 2019

The F3Net is able to segment salient object regions accurately and provide clear local details and outperforms state-of-the-art approaches on six evaluation metrics.

803 0

Uncertainty Inspired RGB-D Saliency Detection

Deng-Ping Fan, Yuchao Dai, Nick Barnes, F. Saleh, Saeed Anwar, Jing Zhang, Sadegh Aliakbarian•Sun Sep 06 2020

Qualitative and quantitative results on six challengingRGB-D benchmark datasets show the first stochastic framework to employ uncertainty for RGB-D saliency detection by learning from the data labeling process superior performance in learning the distribution of saliency maps.

156 0

P2T: Pyramid Pooling Transformer for Scene Understanding

Mingg-Ming Cheng, Yun Liu, Yu-Huan Wu•Mon Jun 21 2021

This paper proposes to adapt pyramid pooling to Multi-Head Self-Attention (MHSA) in the vision transformer, simultaneously reducing the sequence length and capturing powerful contextual features, in a universal vision transformer backbone, dubbed Pyramid Pooling Transformer (P2T).

291 0

Reverse Attention for Salient Object Detection

Shuhan Chen, Xiuli Tan, Benge Wang, Xuelong Hu•Wed Jul 25 2018

An accurate yet compact deep network for efficient salient object detection that employs residual learning to learn side-output residual features for saliency refinement, which can be achieved with very limited convolutional parameters while keep accuracy.

618 0

Adding a benchmark result helps the community track progress.

RGB Salient Object Detection | State-of-the-Art