Nonparametric Scene Parsing via Label Transfer

By Ce Liu, Jenny Yuen, Antonio Torralba. 2011

398 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

ImageNet Large Scale Visual Recognition Challenge (2014, methodology): “ame each object. The SUN2012 (Xiao et al., 2010) dataset contains 16,873 manually cleaned up and fully annotated images more suitable for standard object detection training and evaluation. SIFT Flow (Liu et al., 2011) contains 2,688 images labeled using the LabelMe system. The LotusHill dataset (Yao”
COCO-Stuff: Thing and Stuff Classes in Context (2016, methodology): “Is stuff easier than things? Several works found that stuff is easier to segment than things [50, 28, 36, 51, 53, 62, 60, 63].”
Pyramid Scene Parsing Network (2016, methodology): “The pioneer scene parsing task [23] is to classify 33 scenes for 2,688 images on LMO dataset [22].”
Semantic Image Segmentation via Deep Parsing Network (2015, background): “wise functions, including long-range dependencies [16, 17], high-order potentials [37, 36], and semantic label contexts [21, 26, 38].”
A Comprehensive Survey on Transfer Learning (2019, methodology): “Therefore, in the final step, the crossdomain dense correspondences are established between the test image and the retrieved best matching image at first, and then the annotations of the best matching image are transferred to the test image via the Markov random field model [180], [181].”
Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts (2016, methodology): “The various scene layouts that we demonstrate on Figure 3 depict various scene types, e.g. urban, mountain, forest, sea, lake, and they correspond to im- ages from SIFTflow [15] and LMSun [24] datasets to insure that neither the original images nor the semantic layouts are previously observed while ”
Unrolling Loopy Top-Down Semantic Feedback in Convolutional Deep Networks (2014, methodology): “The third group includes non-parametric methods, which have also shown to perform very well in image parsing problems [18, 6, 28, 29].”
Semantic Amodal Segmentation (2015, background): “A remarkable property of human perception is the ease with which our visual system interpolates information not directly visible in an image [29].”
Temporal Tessellation: A Unified Approach for Video Analysis (2016, methodology): “ng and using dense correspondences. Brieﬂy, these methods assume that reference images are associated with a semantic channel containing, e.g., per pixel depths [13, 18], semantic segmentation labels [24, 42] and even character labels for text images [15]. Robust dense correspondence methods are the”
The SUN Attribute Database: Beyond Categories for Deeper Scene Understanding (2014, methodology): “Recently, several nonparametric, data-driven approaches have been proposed for the scene parsing problem (Liu et al. 2011; Tighe and Lazebnik 2013; Eigen and Fergus 2012).”
Projective analysis for 3D shape segmentation (2013, methodology): “To find the optimal slab mapping function W (·) and the corresponding dissimilarity value D(T, S), we first compute a slab matching cost matrix M , where each entry is the distance between corresponding slabs: Mi,j = hj ×BiSH(T [rj ], S[ri]).”
Crowdsourcing in Computer Vision (2016, neutral): “Long et al. [2013] learn a Gaussian process to derive the estimate of both the global label noise and the expertise of each individual labeler. Wang et al. [2013] further propose quality-based pricing for crowdsourced workers after estimating the amount of information contributed by each.”
Scene parsing using inference Embedded Deep Networks (2016, methodology): “We apply the proposed networks to scene labeling, and several experiments are conducted on SIFT Flow and PASCAL VOC Dataset.”
Combining the Best of Convolutional Layers and Recurrent Layers: A Hybrid Network for Semantic Segmentation (2016, methodology): “Nonparametric methods have achieved remarkable performance in semantic segmentation [10,11,12,13,14].”
Context Driven Scene Parsing with Attention to Rare Classes (2014, methodology): “An alternative is to use nonparametric approaches [15, 4, 20, 22, 21].”
KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D (2021, methodology): “the per pixel annotation time of individual images, including classical methods [38], [60] and learning based methods [2], [3], [19], [59].”
Learning to segment under various forms of weak supervision (2015, methodology): “Semantic segmentation is one of the most fundamental challenges in computer vision, and conventional fully supervised algorithms have demonstrated promising results [21, 10, 8, 33, 35, 36, 44, 19, 20, 45, 31].”