What Makes a Patch Distinct?

By Ran Margolin, Ayellet Tal, Lihi Zelnik-Manor. 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

537 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/bde473538f4837120ab0349932376c8ffd4a0f53

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

Citations in the corpus

Exploiting Saliency for Object Segmentation from Image Level Labels (2017, methodology): “Like most computer vision areas, hand-crafted methods [14, 28, 8] have now been surpassed by convnet based approaches [53, 22, 21] for object saliency.”
How to Evaluate Foreground Maps (2014, methodology): “We examined the number of times a generic map scored higher than the mean score obtained by the five state-of-theart algorithms [9, 10, 12, 13, 19].”
Anabranch network for camouflaged object segmentation (2019, methodology): “Various patch-based methods were also proposed that estimate dissimilarity between image patches (Cheng et al., 2011; Margolin et al., 2013; Zhang et al., 2015).”
Salient Object Detection: A Benchmark (2015, unknown): “2.24 11 FES [74] Img.Anal. 2011 M + C .096 12 SF [75] CVPR 2012 C .202 13 LMLC [76] TIP 2013 M + C 140. 14 HS [77] CVPR 2013 EXE .528 15 GMR [78] CVPR 2013 M .149 16 DRFI [79] CVPR 2013 C .697 17 PCA [80] CVPR 2013 M + C 4.34 18 LBI [81] CVPR 2013 M + C 251. 19 GC [82] ICCV 2013 C .037 20 CHM [83] I”
Salient Object Detection: A Discriminative Regional Feature Integration Approach (2013, methodology): “The uniqueness can also be captured in a global scope by comparing a patch to its k nearest neighbors [17] or as its distance to the average patch over the image along the principal component axis coordinates [31].”
Depth saliency based on anisotropic center-surround difference (2014, methodology): “We choose three state-of-the-art methods work on color images namely CNTX [9], RC [10], PCA [11] and three depth saliency methods namely CURV [16], SS [13], DP [14] for comparison.”
Crisp Boundary Detection Using Pointwise Mutual Information (2014, unknown): “The utility of internal image statistics has been previously demonstrated in the context of super-resolution and denoising [29] as well as saliency prediction [30].”
Saliency detection by multi-context deep learning (2015, methodology): “Methods for comparison include DRFI [25], HS [56], GBMR [57], PCAS [41], CEOS [40], GC [12], and SF [44].”
Minimum Barrier Salient Object Detection at 80 FPS (2015, background): “Therefore, many salient object detection methods combine the contrast/uniqueness cue with other higher level priors [5, 24, 34, 26, 6], e.”
The Secrets of Salient Object Segmentation (2014, methodology): “-accurate object silhouette masks. Their paper showed that existing xation algorithms perform poorly if benchmarked F-measures of PR curve. Inspired by this new dataset, a line of papers has proposed [9, 23, 22] to tackle this new challenge of predicting full-resolution masks of salient objects. An ”
SuperCNN: A Superpixelwise Convolutional Neural Network for Salient Object Detection (2015, methodology): “12. a Input. b GT. c PCA (Margolin et al. 2013). d GMR (Yang et al. 2013). e HS (Yan et al. 2013). f GC (Ming-Chng et al. 2013). g CBS (Jiang et al. 2011). h RC (Cheng et al. 2011). i CA (Goferman et al. 2010). j Ours (Color figure online) hand-crafted features of the other methods are somewhat…”
Salient Object Detection via Structured Matrix Decomposition (2017, methodology): “(E ) EC SS D Metric SMD DRFI [57] RBD [63] HCT [17] DSR [62] MC [83] MR [61] HS [21] PCA [22] TD [20] GC [23] RC [12] SVO [18] WF↑ 0.”
Deep networks for saliency detection via local estimation and global search (2015, methodology): “We compare the proposed method (LEGS) with ten state-of-the-art models including SVO [4], PCA[26], DRFI [16], GC [6], HS [40], MR [41], UFO [17], wCtr [42], CPMC-GBVS [23] and HDCT [18].”
Recurrent Attentional Networks for Saliency Detection (2016, methodology): “Bottom-up methods [21, 17, 19, 1, 32, 9, 34] make use of level local visual cues like color, contrast, orientation and texture.”
Video Segmentation by Non-Local Consensus voting (2014, methodology): “We use the efficient visual saliency implementation of [24] for every frame separately.”
Salient object detection: A survey (2014, background): “ based techniques [88]. In addition to color uniqueness, distinctiveness of complementary cues such as texture [85] and structure [89] is also considered for salient object detection. Margolin et al. [80] propose to combine the regional uniqueness and patch distinctiveness to form a saliency map. In”
Structure-Measure: A New Way to Evaluate Foreground Maps (2017, methodology): “es are computed on the ASD (a.k.a ASD1000) dataset [1]. The non-binary foreground maps (5000 maps in total) were generated using ﬁve saliency detection models including CA [19], CB [23], RC [13], PCA [35], and SVO [9]. We assign = 0:5 and K= 4 in all experiments. When using a single CPU thread (4 GH”