A systematic comparison between visual cues for boundary detection.

148 citations recorded by the source corpus.

How researchers see this paper

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

EDTER: Edge Detection with Transformer (2022, methodology): “Compared with BSDS500, the annotations of NYUDv2 are unitary, and the scale of Multicue is small, which quickly overﬁts of the model trained on them.”
Holistically-Nested Edge Detection (2015, neutral): “2012), Multicueedge/boundary (Mély et al. 2015), and PASCAL-Context (Everingham et al.”
Bi-Directional Cascade Network for Perceptual Edge Detection (2019, methodology): “With a Human [35] .760 (0.017) – – Multicue [35] .720 (0.014) – – HED [50] .814 (0.011) .822 (0.008) .869(0.015) RCF [30] .817 (0.004) .825 (0.005) – RCF [30] ‡ .825 (0.008) .836 (0.007) – BDCN .836 ( 0.001 ) .846( 0.003 ) .893( 0.001 ) BDCN ‡ .838 (0.004) .853 (0.009) .906 (0.005)”
Deep Structural Contour Detection (2020, background): “Multi-cue dataset [30] is a novel human-labeled object boundary detection dataset.”
Pixel Difference Networks for Efficient Edge Detection (2021, methodology): “We also record the evaluation results on Multicue dataset and the comparison results with other methods are shown on Table 7.”
Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection (2019, methodology): “To the best of our knowledge, the unique dataset for edge detection shared to the community is Multicue Dataset for Boundary Detection (MDBD—2016) [23], which although mainly generated for the boundary detection study, it contains a subset of”