SOTAVerified

Saliency Detection

Saliency Detection is a preprocessing step in computer vision which aims at finding salient objects in an image.

Source: An Unsupervised Game-Theoretic Approach to Saliency Detection

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 201–225 of 364 papers

TitleStatusHype
Towards High-Resolution Salient Object DetectionCode0
In defense of OSVOS—0
TASED-Net: Temporally-Aggregating Spatial Encoder-Decoder Network for Video Saliency DetectionCode0
Contour Loss: Boundary-Aware Learning for Salient Object Segmentation—0
Region Refinement Network for Salient Object Detection—0
Saliency Detection With Fully Convolutional Neural Network—0
Light Field Saliency Detection with Deep Convolutional NetworksCode0
Gravitational Laws of Focus of AttentionCode0
Learning to Explore Intrinsic Saliency for Stereoscopic Video—0
Orthogonal Decomposition Network for Pixel-Wise Binary Classification—0
Co-Saliency Detection via Mask-Guided Fully Convolutional Networks With Multi-Scale Label Smoothing—0
A Mutual Learning Method for Salient Object Detection With Intertwined Multi-SupervisionCode0
DeepCO3: Deep Instance Co-Segmentation by Co-Peak Search and Co-Saliency DetectionCode0
Saliency detection based on structural dissimilarity induced by image quality assessment modelCode0
Synthetic Defocus and Look-Ahead Autofocus for Casual Videography—0
DSAL-GAN: Denoising based Saliency Prediction with Generative Adversarial Networks—0
Multi-source weak supervision for saliency detectionCode0
Salient object detection on hyperspectral images using features learned from unsupervised segmentation taskCode0
Object Discovery From a Single Unlabeled Image by Mining Frequent Itemset With Multi-scale FeaturesCode0
Saliency detection for seismic applications using multi-dimensional spectral projections and directional comparisons—0
Deep Reasoning with Multi-Scale Context for Salient Object Detection—0
Salient Object Detection with Lossless Feature Reflection and Weighted Structural Loss—0
Light-weighted Saliency Detection with Distinctively Lower Memory Cost and Model Size—0
Unsupervised uncertainty estimation using spatiotemporal cues in video saliency detection—0
PiCANet: Pixel-wise Contextual Attention Learning for Accurate Saliency DetectionCode0
Show:102550
← PrevPage 9 of 15Next →
All datasetsDUT-OMRONHKU-ISCAT2000DUTS-testECSSDPASCAL ContextPASCAL-S

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1UCFMAE0.12—Unverified
2U2-Net+MAE0.06—Unverified
3U2-NetMAE0.05—Unverified
4LDF(ours)MAE0.05—Unverified
5Pyramid Feature AttentionMAE0.04—Unverified
#ModelMetricClaimedVerifiedStatus
1U2-Net+MAE0.04—Unverified
2Pyramid Feature AttentionMAE0.03—Unverified
3LDF(ours)MAE0.03—Unverified
#ModelMetricClaimedVerifiedStatus
1SUMAUC0.89—Unverified
2EYMOLAUC0.83—Unverified
#ModelMetricClaimedVerifiedStatus
1Pyramid Feature AttentionMAE0.04—Unverified
2PFAN [zhao2019pyramid] (+) PRNMAE0.04—Unverified
#ModelMetricClaimedVerifiedStatus
1Pyramid Feature AttentionMAE0.03—Unverified
#ModelMetricClaimedVerifiedStatus
1InvPTmax_F184.81—Unverified
#ModelMetricClaimedVerifiedStatus
1Pyramid Feature AttentionMAE0.07—Unverified