Hierarchical Image Saliency Detection on Extended CSSD

By Jianping Shi, Qiong Yan, Li Xu, Jiaya Jia. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016

609 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/7dbd0e26e1a3ec461b506fdf87a2b2d386580e2e

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model (2022, methodology): “As in the implementation of [3,4], we use a mix of single object datasets [13,14,6,19,2].”
Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation (2021, methodology): “Following previous practices [18, 21], we ﬁrst pretrain the model on static image datasets [73, 74, 75, 76, 77] with synthetic deformation then perform main training on YouTubeVOS [78] and DAVIS [3, 65].”
Exploiting Saliency for Object Segmentation from Image Level Labels (2017, background): “Image saliency has multiple connotations, it can refer to a spatial probability map of where a person might look first [48], a probability map of which object a person might look first [23], or a binary mask segmenting the one object a person is most likely to look first [5, 39].”
Saliency Detection via a Multiple Self-Weighted Graph-Based Manifold Ranking (2020, methodology): “8) RES [56], an algorithm that proposes a multilayer method with which to analyze saliency cues and infer the final saliency map by combining all the saliency cues using different scales.”
Reverse Attention for Salient Object Detection (2018, methodology): “We comprehensively evaluated our method on six representative datasets, including MSRA-B [36], HKU-IS [37], ECSSD [38], PASCAL-S [39], SOD [40], and DUT-OMRON [41], which contain 5000, 4447, 1000, 850, 300, 5168 well annotated images, respectively.”
Segment Anything in High Quality (2023, methodology): “HQSeg-44K is a collection of six existing image datasets including DIS [34] (train set), ThinObject-5K [29] (train set), FSS [26], ECSSD [37], MSRA-10K [8], DUT-OMRON [45] with extremely fine-grained mask labeling, where each of them contains 7.4K mask labels on average.”
STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation (2015, background): “, Hierarchical Saliency (HS) [21] detection method.”
Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation (2017, background): “Alternatively, the salient object detection view generates a binary mask that detects important regions from natural images [29].”
Recurrent Attentional Networks for Saliency Detection (2016, methodology): “To further evaluate the proposed method “CNN-DecNN + RACDNN”, we compare it with two recent deep learningbased saliency detection methods (MCDL [49] and MDF [29]) on HKUIS, ECSSD, and SED2 datasets.”
Weakly- and Semi-Supervised Panoptic Segmentation (2018, methodology): “Note that saliency priors, used by many works such as [10, 31, 32] on Pascal VOC, are not suitable for “stuff” classes as popular saliency datasets [34–36] only consider “things” to be salient.”
Learning Video Object Segmentation from Static Images (2016, methodology): “We consider images and segmentation masks from ECSSD [41], MSRA10K [9], SOD [28], and PASCAL-S [25].”
Understanding Deep Learning Techniques for Image Segmentation (2019, neutral): “Natural Berkeley Segmentation Dataset [140] Scenes PASCAL VOC [54] Stanford Background Dataset [72] Microsoft COCO [122] MIT Scene parsing data(ADE20K) [222, 223] Semantic Boundaries Dataset [75] Microsoft Research Cambridge Object Recognition Image Database (MSRC) [188] Video Densely Annotated Vide”
Associating Objects with Transformers for Video Object Segmentation (2021, methodology): “Training Details: Following [46, 26, 23, 34], the training stage is divided into two phases: (1) pre-training on sythetic video sequence generated from static image datasets [14, 21, 10, 36, 15] by”
New Contour Cue-Based Hybrid Sparse Learning for Salient Object Detection (2019, methodology): “To achieve comprehensive evaluation, we conduct extensive experiments on four benchmark saliency datasets, including PASCAL-S (850 images) [64], ECSSD (1000 images) [65], DUT-OMRON (5168 images) [30], and THUS-10000 (10 000 images) [17].”
Video Object Segmentation Using Space-Time Memory Networks (2019, methodology): “We trained our model through two training stages: the pre-training on static images [29, 5, 7, 8, 19] and the main Memory frame(s) Youtube -VOS DAVIS Time 2016 2017”
Fast Video Object Segmentation by Reference-Guided Mask Propagation (2018, methodology): “We used the saliency detection datasets [34, 8] to segment foreground objects and the Pascal VOC dataset [10, 14] for background images.”
Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation (2020, positive): “However, to learn more general and robust feature correspondence, these data-hungry methods may require backbones pretrained on extra data with mask annotations from other tasks such as instance segmentation [14] or saliency detection [15].”