Decorrelation and Distinctiveness Provide with Human-Like Saliency

García-Díaz, Antón; Fdez-Vidal, Xosé R.; Pardo, Xosé M.; Dosil, Raquel

doi:10.1007/978-3-642-04697-1_32

Cited by 58 publications

(49 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, it has been shown that humans look at the center objects [61,62]. Some saliency models implicitly emphasize the central parts of objects (e.g, [17]). Explicit central object-bias may lead to even higher fixation predic-tion accuracies.…”

Section: Discussionmentioning

confidence: 99%

Analysis of Scores, Datasets, and Models in Visual Saliency Prediction

Borji

Tavakoli

Sihite

et al. 2013

2013 IEEE International Conference on Computer Vision

198

115

View full text Add to dashboard Cite

Significant recent progress has been made in developing high-quality saliency models. However, less effort has been undertaken on fair assessment of these models, over large standardized datasets and correctly addressing confounding factors. In this study, we pursue a critical and quantitative look at challenges (e.g., center-bias, map smoothing) in saliency modeling and the way they affect model accuracy. We quantitatively compare 32 state-of-the-art models (using the shuffled AUC score to discount center-bias) on 4 benchmark eye movement datasets, for prediction of human fixation locations and scanpath sequence. We also account for the role of map smoothing. We find that, although model rankings vary, some (e.g., AWS, LG, AIM, and HouNIPS) consistently outperform other models over all datasets. Some models work well for prediction of both fixation locations and scanpath sequence (e.g., Judd, GBVS). Our results show low prediction accuracy for models over emotional stimuli from the NUSEF dataset. Our last benchmark, for the first time, gauges the ability of models to decode the stimulus category from statistics of fixations, saccades, and model saliency values at fixated locations. In this test, ITTI and AIM models win over other models. Our benchmark provides a comprehensive high-level picture of the strengths and weaknesses of many popular models, and suggests future research directions in saliency modeling.

show abstract

Section: Discussionmentioning

confidence: 99%

Analysis of Scores, Datasets, and Models in Visual Saliency Prediction

Borji

Tavakoli

Sihite

et al. 2013

2013 IEEE International Conference on Computer Vision

198

115

View full text Add to dashboard Cite

show abstract

“…Some others have further used graph-cut or grab-cub algorithms to refine borders of their saliency maps and count for salient object contours [23] [13]. While some methods define visual saliency in a local way (e.g., Itti et al [2], SEO [8], GBVS [3], AWS [7], and DAKlein [25]), some others are based on global rarity of image regions over the entire scene (e.g., AIM [4], SUN [10], HouNIPS [6], HouCVPR [5], and RC [13]). …”

Section: Related Workmentioning

confidence: 99%

Salient Object Detection: A Benchmark

Borji

Sihite

Itti

2012

Lecture Notes in Computer Science

636

768

View full text Add to dashboard Cite

Abstract. Several salient object detection approaches have been published which have been assessed using different evaluation scores and datasets resulting in discrepancy in model comparison. This calls for a methodological framework to compare existing models and evaluate their pros and cons. We analyze benchmark datasets and scoring techniques and, for the first time, provide a quantitative comparison of 35 stateof-the-art saliency detection models. We find that some models perform consistently better than the others. Saliency models that intend to predict eye fixations perform lower on segmentation datasets compared to salient object detection algorithms. Further, we propose combined models which show that integration of the few best models outperforms all models over other datasets. By analyzing the consistency among the best models and among humans for each scene, we identify the scenes where models or humans fail to detect the most salient object. We highlight the current issues and propose future research directions.

show abstract

“…As reference for comparisons, we consider 11 stateof-the-art saliency algorithms: GBVS [10], the multiscale quaternion DCT signature on YUV input (denoted ∆QDCT) [28], Judd [18], AWS [8], CovSal [6] (with covariances + means), Tavakoli [30], AIM [5], Goferman [9], ICL [13], Image Signature (with LAB color space) [11], and Boost [4], all with default parameters. This selection is based on the top-performing models from two recent and comprehensive reviews/taxonomies [4,16].…”

Section: Evaluation Protocolmentioning

confidence: 99%

Large-Scale Optimization of Hierarchical Features for Saliency Prediction in Natural Images

Vig

Dörr

Cox

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

369

226

View full text Add to dashboard Cite

Saliency prediction typically relies on hand-crafted (multiscale) features that are combined in different ways to form a "master" saliency map, which encodes local image conspicuity. Recent improvements to the state of the art on standard benchmarks such as MIT1003 have been achieved mostly by incrementally adding more and more hand-tuned features (such as car or face detectors) to existing models [18,4,22,34]. In contrast, we here follow an entirely automatic data-driven approach that performs a large-scale search for optimal features. We identify those instances of a richly-parameterized bio-inspired model family (hierarchical neuromorphic networks) that successfully predict image saliency. Because of the high dimensionality of this parameter space, we use automated hyperparameter optimization to efficiently guide the search. The optimal blend of such multilayer features combined with a simple linear classifier achieves excellent performance on several image saliency benchmarks. Our models outperform the state of the art on MIT1003, on which features and classifiers are learned. Without additional training, these models generalize well to two other image saliency data sets, Toronto and NUSEF, despite their different image content. Finally, our algorithm scores best of all the 23 models evaluated to date on the MIT300 saliency challenge [16], which uses a hidden test set to facilitate an unbiased comparison.

show abstract

Decorrelation and Distinctiveness Provide with Human-Like Saliency

Cited by 58 publications

References 19 publications

Analysis of Scores, Datasets, and Models in Visual Saliency Prediction

Analysis of Scores, Datasets, and Models in Visual Saliency Prediction

Salient Object Detection: A Benchmark

Large-Scale Optimization of Hierarchical Features for Saliency Prediction in Natural Images

Contact Info

Product

Resources

About