Papers › A Dilated Inception Network for Visual Saliency Prediction

A Dilated Inception Network for Visual Saliency Prediction

7 Apr 2019arXiv:1904.03571archive 2025-07-28

Sheng Yang, Guosheng Lin, Qiuping Jiang, Weisi Lin

Recently, with the advent of deep convolutional neural networks (DCNN), the improvements in visual saliency prediction research are impressive. One possible direction to approach the next improvement is to fully characterize the multi-scale saliency-influential factors with a computationally-friendly module in DCNN architectures. In this work, we proposed an end-to-end dilated inception network (DINet) for visual saliency prediction. It captures multi-scale contextual features effectively with very limited extra parameters. Instead of utilizing parallel standard convolutions with different kernel sizes as the existing inception module, our proposed dilated inception module (DIM) uses parallel dilated convolutions with different dilation rates which can significantly reduce the computation load while enriching the diversity of receptive fields in feature maps. Moreover, the performance of our saliency model is further improved by using a set of linear normalization-based probability distribution distance metrics as loss functions. As such, we can formulate saliency prediction as a probability distribution prediction task for global saliency inference instead of a typical pixel-wise regression problem. Experimental results on several challenging saliency benchmark datasets demonstrate that our DINet with proposed loss functions can achieve state-of-the-art performance with shorter inference time.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ysyscool/DINet officialmentioned in papermentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DiversityPredictionSaliency PredictionVideo Saliency Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Saliency Detection MSU Video Saliency Prediction DINet AUC-J 0.858 #6 of 14 Archive leaderboard report
Video Saliency Detection MSU Video Saliency Prediction DINet CC 0.671 #6 of 14 Archive leaderboard report
Video Saliency Detection MSU Video Saliency Prediction DINet FPS 4.85 #6 of 14 Archive leaderboard report
Video Saliency Detection MSU Video Saliency Prediction DINet KLDiv 0.575 #6 of 14 Archive leaderboard report
Video Saliency Detection MSU Video Saliency Prediction DINet NSS 1.85 #6 of 14 Archive leaderboard report
Video Saliency Detection MSU Video Saliency Prediction DINet SIM 0.592 #6 of 14 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionConvolutionDCNNInception ModuleMax Pooling

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections