BSDS500
13 papers with code • 2 benchmarks • 0 datasets
Benchmarks
These leaderboards are used to track progress in BSDS500
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
Most implemented papers
Object Contour Detection with a Fully Convolutional Encoder-Decoder Network
We develop a deep learning algorithm for contour detection with a fully convolutional encoder-decoder network.
Richer Convolutional Features for Edge Detection
yun-liu/rcf
•
•
CVPR 2017
Using VGG16 network, we achieve \sArt results on several available datasets.
Photo-Sketching: Inferring Contour Drawings from Images
Edges, boundaries and contours are important subjects of study in both computer graphics and computer vision.
Bi-Directional Cascade Network for Perceptual Edge Detection
Exploiting multi-scale representations is critical to improve edge detection for objects at different scales.
Object Contour and Edge Detection with RefineContourNet
A ResNet-based multi-path refinement CNN is used for object contour detection.
Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation
We propose a unified approach for bottom-up hierarchical image segmentation and object proposal generation for recognition, called Multiscale Combinatorial Grouping (MCG).
AMAT: Medial Axis Transform for Natural Images
We introduce Appearance-MAT (AMAT), a generalization of the medial axis transform for natural images, that is framed as a weighted geometric set cover problem.
Superpixel Segmentation via Convolutional Neural Networks with Regularized Information Maximization
We propose an unsupervised superpixel segmentation method by optimizing a randomly-initialized convolutional neural network (CNN) in inference time.
Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation
JianqiangWan/Super-BPD
•
•
CVPR 2020
In this paper, we propose a fast image segmentation method based on a novel super boundary-to-pixel direction (super-BPD) and a customized segmentation algorithm with super-BPD.
Unmixing Convolutional Features for Crisp Edge Detection
WHUHLX/CATS
•
•
This paper presents a context-aware tracing strategy (CATS) for crisp edge detection with deep edge detectors, based on an observation that the localization ambiguity of deep edge detectors is mainly caused by the mixing phenomenon of convolutional neural networks: feature mixing in edge classification and side mixing during fusing side predictions.
