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-7

Saliency Prediction

3260 papers • 126 benchmarks • 313 datasets

A saliency map is a model that predicts eye fixations on a visual scene. Saliency prediction is informed by the human visual attention mechanism and predicts the possibility of the human eyes to stay in a certain position in the scene.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in saliency-prediction-21

Trend

Dataset

Best Model

Actions

SALECI

SALECI

MIT300

MIT300

SALICON

SALICON

Libraries

i

Use these libraries to find saliency-prediction-21 models and implementations

taozh2017/RGBD-SODsurvey

2 papers 316

Datasets

SALICON

iSUN

UIEB

SUIM

MSU Video Saliency Prediction

MSU Video Saliency Prediction

Salient-KITTI

Subtasks

Few-Shot Transfer Learning for Saliency Prediction Aerial Video Saliency Prediction

Most implemented papers

Contextual Encoder-Decoder Network for Visual Saliency Prediction

Alexander Kroner, M. Senden, K. Driessens, R. Goebel•Sun Feb 17 2019

This work proposes an approach based on a convolutional neural network pre-trained on a large-scale image classification task that achieves competitive and consistent results across multiple evaluation metrics on two public saliency benchmarks and demonstrates the effectiveness of the suggested approach on five datasets and selected examples.

210

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

CapMIT1003

CapMIT1003

0

Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception

M. Islam, Peigen Luo, Junaed Sattar•Mon Feb 03 2020

Deep SESR is presented, a residual-in-residual network-based generative model that can learn to restore perceptual image qualities at 2x, 3x, or 4x higher spatial resolution and formulating a multi-modal objective function that addresses the chrominance-specific underwater color degradation, lack of image sharpness, and loss in high-level feature representation.

254 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

SalGAN: Visual Saliency Prediction with Generative Adversarial Networks

Jordi Torres, C. Canton-Ferrer, Kevin McGuinness, N. O’Connor, Junting Pan, Xavier Giro-i-Nieto, E. Sayrol•Tue Jan 03 2017

This work introduces SalGAN, a deep convolutional neural network for visual saliency prediction trained with adversarial examples and shows how adversarial training allows reaching state-of-the-art performance across different metrics when combined with a widely-used loss function like BCE.

422 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

Fast Underwater Image Enhancement for Improved Visual Perception

M. Islam, Junaed Sattar, Youya Xia•Fri Mar 22 2019

The proposed conditional generative adversarial network-based model is suitable for real-time preprocessing in the autonomy pipeline by visually-guided underwater robots and provides improved performances of standard models for underwater object detection, human pose estimation, and saliency prediction.

1234 0

BASNet: Boundary-Aware Salient Object Detection

Xuebin Qin, Masood Dehghan, Martin Jägersand, Chenyang Huang, Chao Gao•Fri May 31 2019

Deep Convolutional Neural Networks have been adopted for salient object detection and achieved the state-of-the-art performance. Most of the previous works however focus on region accuracy but not on the boundary quality. In this paper, we propose a predict-refine architecture, BASNet, and a new hybrid loss for Boundary-Aware Salient object detection. Specifically, the architecture is composed of a densely supervised Encoder-Decoder network and a residual refinement module, which are respectively in charge of saliency prediction and saliency map refinement. The hybrid loss guides the network to learn the transformation between the input image and the ground truth in a three-level hierarchy -- pixel-, patch- and map- level -- by fusing Binary Cross Entropy (BCE), Structural SIMilarity (SSIM) and Intersection-over-Union (IoU) losses. Equipped with the hybrid loss, the proposed predict-refine architecture is able to effectively segment the salient object regions and accurately predict the fine structures with clear boundaries. Experimental results on six public datasets show that our method outperforms the state-of-the-art methods both in terms of regional and boundary evaluation measures. Our method runs at over 25 fps on a single GPU. The code is available at: https://github.com/NathanUA/BASNet.

1352 0

Semantic Segmentation of Underwater Imagery: Dataset and Benchmark

M. Islam, Chelsey Edge, Yuyang Xiao, Peigen Luo, Muntaqim Mehtaz, Christopher Morse, Sadman Sakib Enan, Junaed Sattar•Wed Apr 01 2020

The first large-scale dataset for semantic Segmentation of Underwater IMagery (SUIM) is presented and SUIM-Net, a fully-convolutional deep residual model that balances the trade-off between performance and computational efficiency is presented.

293 0

A deep multi-level network for saliency prediction

Marcella Cornia, L. Baraldi, R. Cucchiara, G. Serra•Sun Sep 04 2016

This paper proposes an architecture which combines features extracted at different levels of a Convolutional Neural Network (CNN) which outperforms under all evaluation metrics on the SALICON dataset, and achieves competitive results on the MIT300 benchmark.

362 0

Specificity-preserving RGB-D saliency detection

Deng-Ping Fan, Ling Shao, H. Fu, Yi Zhou, Tao Zhou, Geng Chen•Tue Aug 17 2021

A novel framework, the specificity-preserving network (SPNet), which improves SOD performance by exploring both the shared information and modality-specific properties, and which outperforms cutting-edge approaches on six popular RGB-D SOD and three camouflaged object detection benchmarks.

206 0

Adding a benchmark result helps the community track progress.

Saliency Prediction | State-of-the-Art