Hierarchical Saliency Detection Supplementary Material
نویسندگان
چکیده
We introduced a new metric in Sec. 3.1 of our paper, which is defined by the encompassment relation, to measure region scale. The metric is used to merge small-size regions. Since direct computing encompassment is relatively costly, we resort to a fast method by spatial convolution. Given a map M with each pixel labeled by its region index in the region list R, we apply a box filter kt of size t× t, which produces a blurred map kt ◦M (◦ denotes 2D convolution). With computation of absolute differenceDt = |M − kt ◦M |, we screen out regions inR with their scales smaller than t. The scale for a region Ri is smaller than t if and only if ( min y {Dt(y)|y ∈ Ri} ) > 0, (1)
منابع مشابه
Local Background Enclosure for RGB-D Salient Object Detection - Supplementary Results
The purpose of this supplementary material is to examine in detail the contributions of our proposed Local Background Enclosure (LBE) feature. A comparison of LBE with the contrast based depth features used in state-of-the-art salient object detection systems is presented. The LBE feature is compared with the raw depth features ACSD [1], DC [3] and a signed version of DC denoted SDC on the RGBD...
متن کاملSaliency Detection: A Boolean Map Approach Supplementary Materials
Saliency map samples for eye fixation prediction are shown in Fig 1-2; saliency map samples for salient object detection are shown in Fig 3-7. A model of saliency-based visual attention for rapid scene analysis.
متن کاملDeep Networks for Saliency Detection via Local Estimation and Global Search Supplementary Material
We evaluate our method (LEGS) on four benchmark data sets (MSRA-5000 [7], SOD [9], ECCSD [10] and PASCALS [6]) against ten state-of-the-art models (SVO [1], PCA [8], DRFI [3], GC [2], HS [10], MR [11], UFO [4], wCtr [12], CPMC-GBVS [6] and HDCT [5]). We use either the implementations or the saliency maps provided by the authors for fair comparison. Since the DRFI method is also trained on the M...
متن کاملGraph-based Visual Saliency Model using Background Color
Visual saliency is a cognitive psychology concept that makes some stimuli of a scene stand out relative to their neighbors and attract our attention. Computing visual saliency is a topic of recent interest. Here, we propose a graph-based method for saliency detection, which contains three stages: pre-processing, initial saliency detection and final saliency detection. The initial saliency map i...
متن کاملSupplementary Materials for ‘ Salient Object Detection : A Discriminative Regional Feature Integration Approach ’
In this supplementary material, we will present more details on learning a Random Forest saliency regressor. More evaluation results with state-of-the-art algorithms are also presented. F 1 LEARNING 1.1 Learning a Similarity Score between Two Adjacent Superpixels To learn the similarity score of two adjacent superpixels si and sj , they are described by a 222dimensional feature vector, includin...
متن کامل