Saliency Aggregation: Does Unity Make Strength?

Meur, Olivier Le; Li, Zhi

doi:10.1007/978-3-319-16817-3_2

Cited by 13 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This indicates that several models are affected by a bias imposed by some former datasets (i.e., ASD) which is the existence of only one object in the image. Aggregation of saliency models for building a strong prediction model (similar to [1], [120], [121], and behavioral investigation of saliency judgments by humans (e.g., [21], [122]) are two other interesting directions. The relationship (similarity and difference) between salient object detection and related fields such as object detection, object proposals, general segmentation, and fixation prediction 5 and the ways these areas can benefit from each other still remains to be explored further.…”

Section: Discussionmentioning

confidence: 99%

Salient Object Detection: A Benchmark

Borji

Cheng

Jiang

et al. 2015

IEEE Trans. on Image Process.

1,280

312

View full text Add to dashboard Cite

We extensively compare, qualitatively and quantitatively, 41 state-of-the-art models (29 salient object detection, 10 fixation prediction, 1 objectness, and 1 baseline) over seven challenging data sets for the purpose of benchmarking salient object detection and segmentation methods. From the results obtained so far, our evaluation shows a consistent rapid progress over the last few years in terms of both accuracy and running time. The top contenders in this benchmark significantly outperform the models identified as the best in the previous benchmark conducted three years ago. We find that the models designed specifically for salient object detection generally work better than models in closely related areas, which in turn provides a precise definition and suggests an appropriate treatment of this problem that distinguishes it from other problems. In particular, we analyze the influences of center bias and scene complexity in model performance, which, along with the hard cases for the state-of-the-art models, provide useful hints toward constructing more challenging large-scale data sets and better saliency models. Finally, we propose probable solutions for tackling several open problems, such as evaluation scores and data set bias, which also suggest future research directions in the rapidly growing field of salient object detection.

show abstract

Section: Discussionmentioning

confidence: 99%

Salient Object Detection: A Benchmark

Borji

Cheng

Jiang

et al. 2015

IEEE Trans. on Image Process.

1,280

312

View full text Add to dashboard Cite

show abstract

“…The most used is average weights which is uniform and spatial invariant, w i = 1/m. We call it AVG for short, which is verified by Borji [8] and Le Meur [7] and can produce satisfied aggregation results.…”

Section: Linear Aggregationmentioning

confidence: 82%

“…In [6], Li et al proposed a saliency detection method whose final step is Bayes integration of two saliency maps generated by dense and sparse reconstruction errors respectively. Focusing on eye fixation prediction, Le Meur et al [7] made a detailed comparison of various aggregation methods including unsupervised and learning-based schemes, in which got the following conclusions: a simple average of the top two saliency maps significantly outperforms each individual one, and considering more saliency maps tends to decrease the performance. Similar to this work, Borji et al [8] proposed two combining strategies: Naive Bayesian evidence accumulation and linear summation, which also demonstrated aggregation results working better than individual ones.…”

Section: Introductionmentioning

confidence: 99%

A Comparative Study of Saliency Aggregation for Salient Object Detection

Chen

Zheng

et al. 2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A variety of saliency detection methods have been proposed in recently, which often complement each other. In this study, we try to improve their performances by aggregating these individual ones. First, we propose an improved Bayes aggregation method with double thresholds. Then, we compare it with five other aggregation approaches on four benchmark datasets. Experiments show that all the aggregation methods significantly outperform each individual one. Among these aggregation methods, average and Non-negative Matrix Factorization (NMF) weights perform best in terms of precision-recall curve, our Bayes is very close to them. While for mean absolute error score, NMF and our Bayes perform best. We also find that it is possible to further improve their performance by using more accurate reference map. The ideal is ground truth, of course. Our results could have an important impact for applications required robust and uniform saliency maps.

show abstract

“…Combining (Harel et al, 2006) and (Riche et al, 2013) models (called Top2(R+H) in Table 2) significantly increases the performance, compared to the best performing saliency model, i.e. (Riche et al, 2013)'s model (see (Le Meur & Liu, 2014) for more 435 details on saliency aggregation). When the Top2(R+H) saliency maps are used as input of (Le Meur & Liu, 2015)'s model, the capacity to predict salient areas is getting higher than the Top2(R+H) model alone.…”

Section: Bottom-up Salience and Viewing Biases For Predicting Visual mentioning

confidence: 99%

Introducing context-dependent and spatially-variant viewing biases in saccadic models

Meur

Coutrot

2016

Vision Research

View full text Add to dashboard Cite

Previous research showed the existence of systematic tendencies in viewing behavior during scene exploration. For instance, saccades are known to follow a positively skewed, long-tailed distribution, and to be more frequently initiated in the horizontal or vertical directions. In this study, we hypothesize that these viewing biases are not universal, but are modulated by the semantic visual category of the stimulus. We show that the joint distribution of saccade amplitudes and orientations significantly varies from one visual category to another. These joint distributions are in addition spatially variant within the scene frame. We demonstrate that a saliency model based on this better understanding of viewing behavioral biases and blind to any visual information outperforms well-established saliency models. We also propose a saccadic model that takes into account classical low-level features and spatially-variant and context-dependent viewing biases. This model outperforms state-of-the-art saliency models, and provides scanpaths in close agreement with human behavior. The better description of viewing biases will not only improve current models of visual attention but could also influence many other applications such as the design of human-computer interfaces, patient diagnosis or image/video processing applications.

show abstract

Saliency Aggregation: Does Unity Make Strength?

Cited by 13 publications

References 26 publications

Salient Object Detection: A Benchmark

Salient Object Detection: A Benchmark

A Comparative Study of Saliency Aggregation for Salient Object Detection

Introducing context-dependent and spatially-variant viewing biases in saccadic models

Contact Info

Product

Resources

About