Decomposing a scene into geometric and semantically consistent regions

By Stephen Gould, Richard Fulton, Daphne Koller. 2009

799 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

ImageNet Large Scale Visual Recognition Challenge (2014, methodology): “, but it is not available for free. Several datasets provide pixel-level segmentations: for example, MSRC dataset (Criminisi, 2004) with 591 images and 23 object classes, Stanford Background Dataset (Gould et al., 2009) with 715 images and 8 classes, and the Berkeley Segmentation dataset (Arbelaez e”
COCO-Stuff: Thing and Stuff Classes in Context (2016, methodology): “For the task of semantic segmentation, the Stanford Background dataset [24] offers pixel-level annotations for seven common stuff categories and a single foreground category (confounding all thing classes).”
Deep Visual-Semantic Alignments for Generating Image Descriptions (2014, neutral): “We ﬁrst present a model that aligns segments of sentences to the visual regions that they describe through a multimodal embedding.”
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (2018, methodology): “There are several model variants proposed to exploit the contextual information for segmentation [28, 65, 36, 39, 22, 79, 51, 14], including those that employ multi-scale inputs (i.”
Rethinking Atrous Convolution for Semantic Image Segmentation (2017, background): “It has been shown that global features or contextual interactions [28, 65, 36, 40, 22, 77] are beneficial in correctly classifying pixels for semantic segmentation.”
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation (2015, methodology): “interesting result here is the large performance improvement in class average and mIOU metrics that is obtained when a large training dataset, obtained by combining [21], [25], [59], [60], is used to train SegNet.”
Material recognition in the wild with the Materials in Context Database (2014, neutral): “For segmentation or scene parsing tasks, per-pixel segmentations are required [22, 8].”
Searching for Efficient Multi-Scale Architectures for Dense Image Prediction (2018, background): “A critical element of building such systems is supplying global features and context information to perform pixel-level classiﬁcation [35, 78, 41, 45, 31, 92, 60, 19, 63].”
Object-Contextual Representations for Semantic Segmentation (2019, methodology): “There exist many region-wise segmentation methods [1,2,21,20,64,50,2,60] that organize the pixels into a set of regions (usually super-pixels), and then classify each region to get the image segmentation result.”
Recurrent Convolutional Neural Networks for Scene Parsing (2013, background): “…efd(Ii,j,k;(W,b)) (4) The parameters (W,b) are learned in an end-to-end supervised way, by minimizing the negative log-likelihood over the training set: L(W,b) = − ∑ I(i,j,k) ln p(li,j,k|Ii,j,k; (W,b)) , (5) where li,j,k is the correct pixel label class, at position (i, j) in image Ik.”
Indoor Semantic Segmentation using depth information (2013, background): “Most datasets employed for semantic image segmentation [11, 17] present the objects centered into the images, under nice lightening conditions.”
Modeling Visual Context is Key to Augmenting Object Detection Datasets (2018, methodology): “To encode more structure, graphical models were then widely used in order to jointly model appearance, geometry, and contextual relations [19,20].”
DeeperLab: Single-Shot Image Parser (2019, background): “For example, it has been known that contextual information is essential for pixel labeling [23, 24, 25, 26, 27, 28, 29].”
Image Segmentation Using Deep Learning: A Survey (2020, neutral): “Stanford Background [156] comprises outdoor images of scenes from existing datasets, such as LabelMe, MSRC, and PASCAL VOC.”
Semantic Segmentation using Adversarial Networks (2016, methodology): “The Stanford Background dataset [10] contains 715 images of eight classes of scene elements.”
Understanding Deep Learning Techniques for Image Segmentation (2019, background): “various semantic 5 Table 1: A list of various datasets in the image segmentation domain Category Dataset 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]”
Region-based Segmentation and Object Detection (2009, methodology): “Gould et al. [ 7 ] provides a complete description of the scene using dynamically evolving decompositions that explain every pixel (both semantically and geometrically).”
A survey on deep learning techniques for image and video semantic segmentation (2018, background): “KITTI-Zhang [42] Urban/Driving 2015 10 2D/3D 1226× 370 ✗ R 140 N/A 112 Stanford background [43] Outdoor 2009 8 2D 320× 240 ✗ R 725 N/A N/A SiftFlow [44] Outdoor 2011 33 2D 256× 256 ✗ R 2688 N/A N/A Youtube-Objects-Jain [45] Objects 2014 10 2D 480× 360 ✓ R 10167 N/A N/A Adobe’s Portrait Segmentation ”
Deep Visual-Semantic Alignments for Generating Image Descriptions (2017, background): “Several works [27] [12] [9] studied the problem of holistic scene understanding in which the scene type, objects and their spatial support in the image is inferred.”
Pedestrian detection aided by deep learning semantic tasks (2014, background): “3 (a), including CamVid (B) [3], Stanford Background (B) [12], and LM+SUN (B) [29], where hard negatives are chosen by applying a simple yet fast pedestrian detector [7] on these datasets.”