Are spatial and global constraints really necessary for segmentation?

By Aurélien Lucchi, Yunpeng Li, Xavier Boix, Kevin Smith, Pascal Fua. 2011

74 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

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs (2016, methodology): “CRFs have been broadly used in semantic segmentation to combine class scores computed by multi-way classifiers with the low-level information captured by the local interactions of pixels and edges [23], [24] or superpixels [25].”
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs (2014, methodology): “In order to deal with the spatial localization issues outlined in the beginning of the introduction, Long et al. (2014) upsample and concatenate the scores from inter-mediate feature maps, while Eigen & Fergus (2014) reﬁne the prediction result from coarse to ﬁne by propagating the coarse results…”
Pyramid Scene Parsing Network (2016, background): “These results should be excluded so that the whole object is either skyscraper or building, but not both.”
Feedforward semantic segmentation with zoom-out features (2014, neutral): “A study in [27] concluded that non-unary terms may be unnecessary when neighborhood and global information is captured by unary terms, but the results were significantly inferior to state of the art at the time.”
Learning Human Pose Estimation Features with Convolutional Networks (2013, background): “This echos what many other researchers, like those in the speech recognition, object recognition, and other domains have experienced [26].”
Fast-SCNN: Fast Semantic Segmentation Network (2019, methodology): “Later, inspired by global image-level context prior to DCNNs [13, 16], the pyramid pooling module of PSPNet [37] and atrous spatial pyramid pooling (ASPP) of DeepLab [4] are employed to encode and utilize global context.”
Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition (2019, background): “Leveraging scene context is useful for object detection [40, 7, 11, 13], semantic segmentation [35, 39, 40, 69], predicting invisible things [32], and action recognition without looking at the human [23, 54].”
Contextual classification of lidar data and building object detection in urban areas (2014, methodology): “We think that the type of geometrical pairwise model used in Lucchi et al. (2011) (‘‘sky should appear above grass’’) is not applicable to remote sensing images, because it requires the definition of an absolute reference direction (e.g. the vertical in images having a horizontal viewing direction).”
Learning a Dictionary of Shape Epitomes with Applications to Image Labeling (2013, methodology): “[22] proposed the Class Independent Model (CIM) to decompose the global node into |L| global nodes.”