Multi-scale Improves Boundary Detection in Natural Images

By Xiaofeng Ren. 2008

207 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

Holistically-Nested Edge Detection (2015, methodology): “This integrated learning of hierarchical features is in distinction to previous multi-scale approaches [38, 39, 28] in which scale-space edge ﬁelds are neither automatically learned nor connected hierarchically.”
Fast Edge Detection Using Structured Forests (2014, methodology): “Ren and Bo [41] improved the result of [1] by computing gradients across learned sparse codes of patch gradients.”
Oriented edge forests for boundary detection (2014, background): “Consistent with the findings of [20], the combined model greatly outperforms any fixed-scale model.”
DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection (2015, background): “However, obvious performance gap is still observed between contour detections given by the algorithms and human annotations.”
Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction (2017, background): “The ability to effectively exploit multi-scale feature representations is considered a crucial factor for achieving accurate predictions of contours in both traditional [29] and CNN-based [38, 19, 24] approaches.”
Object Skeleton Extraction in Natural Images by Fusing Scale-Associated Deep Side Outputs (2016, methodology): “So summing up the multi-scale detection responses, which is adopted in the fusion layer in HED, is able to improve the performance of edge detection [22, 10, 26], while bringing noises across the scales for skeleton extraction.”
From contours to regions: An empirical evaluation (2009, background): “There have been significant advances in contour detection in the last few years [16] [37] [27] [12] [48] [22] [36].”
Generalized Boundaries from Multiple Image Interpretations (2012, methodology): “We argue that in order to confidently classify boundary pixels and robustly combine multiple layers of information, one must consider much larger neighborhoods, in line with recent methods [1], [27], [37].”
Structured Forests for Fast Edge Detection (2013, methodology): “Ren and Bo [31] adopted the data for edge detection allowing for testing edge detectors using multiple modalities including RGB, depth, and RGBD.”
Bi-Directional Cascade Network for Perceptual Edge Detection (2019, background): “[39] show that considering multi-scale cues does improve performance of edge detection.”
Contour Detection and Hierarchical Image Segmentation (2011, methodology): “Ren [28] finds benefit in combining information from multiple scales of the local operators developed by [2].”
Richer Convolutional Features for Edge Detection (2016, background): “Later, researchers tended to manually design features using low-level cues such as intensity, gradient, and texture, and then employ sophisticated learning paradigm to classify edge and non-edge pixels [13, 44].”
Medical Image Analysis using Convolutional Neural Networks: A Review (2017, background): “Generally, segmentation is useful in image processing based applications like biometrics [15, 16], contour detection [17], object matching [18] and object recognition [19].”
A Particle Filter Framework for Contour Detection (2012, background): “Ren [3] first improved this approach by handling these local features at different scales.”
Quantitative analysis of cryo-EM density map segmentation by watershed and scale-space filtering, and fitting of structures by alignment to regions (2010, background): “gions while retaining salient features (Witkin, 1984; Perona and Malik, 1990; Lifshitz et al., 1990; Lindeberg, 1996; Ren, 2008; Braga-Neto and Goutsias, 2005; Leung et al., 2000).”
Deep Spatial-Semantic Attention for Fine-Grained Sketch-Based Image Retrieval (2017, unknown): “, [30, 43]), pose estimation (e.”
Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks (2016, background): “What many of the aforementioned methods have in common is that several simple components contribute to increased performance: (i) information at multiple scales [1], [16], [17], [34], (ii) contour orientation [16], [28], [30], [35], and (iii) end-to-end deep learning [1], [2].”
Machines that learn to segment images: a crucial technology for connectomics. (2010, background): “…it is unrealistic to proceed by simply scaling up a single monolithic computation to an arbitrarily large ﬁeld of view. o One possibility is to modify existing boundary detection techniques to perform multi-scale computation [83], by combining separate computations at multiple spatial resolutions.”
Discriminatively Trained Sparse Code Gradients for Contour Detection (2012, background): “…the availability of datasets with human-marked groundtruth contours, a variety of approaches have been proposed and evaluated (see a summary in [2]), such as learning to classify [17] [20] [16], contour grouping [23] [31] [12], multi-scale features [21] [2], and hierarchical region analysis [2].”