Delving into Crispness: Guided Label Refinement for Crisp Edge Detection

• URL: http://arxiv.org/abs/2306.15172v1
• Date: Tue, 27 Jun 2023 03:12:58 GMT
• Title: Delving into Crispness: Guided Label Refinement for Crisp Edge Detection
• Authors: Yunfan Ye, Renjiao Yi, Zhirui Gao, Zhiping Cai, Kai Xu
• Abstract summary: Learning-based edge detection usually suffers from predicting thick edges. We find that noisy human-labeled edges are the main cause of thick predictions. We propose an effective Canny-guided refinement of human-labeled edges.
• Score: 14.26122188105415
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning-based edge detection usually suffers from predicting thick edges. Through extensive quantitative study with a new edge crispness measure, we find that noisy human-labeled edges are the main cause of thick predictions. Based on this observation, we advocate that more attention should be paid on label quality than on model design to achieve crisp edge detection. To this end, we propose an effective Canny-guided refinement of human-labeled edges whose result can be used to train crisp edge detectors. Essentially, it seeks for a subset of over-detected Canny edges that best align human labels. We show that several existing edge detectors can be turned into a crisp edge detector through training on our refined edge maps. Experiments demonstrate that deep models trained with refined edges achieve significant performance boost of crispness from 17.4% to 30.6%. With the PiDiNet backbone, our method improves ODS and OIS by 12.2% and 12.6% on the Multicue dataset, respectively, without relying on non-maximal suppression. We further conduct experiments and show the superiority of our crisp edge detection for optical flow estimation and image segmentation.

Related papers

• SAUGE: Taming SAM for Uncertainty-Aligned Multi-Granularity Edge Detection [8.651908243317301]
  We unveil that the segment anything model (SAM) provides strong prior knowledge to model the uncertainty in edge labels. Our model uniquely demonstrates strong generalizability for cross-dataset edge detection.
  arXiv  Detail & Related papers  (2024-12-17T13:18:41Z)
• Generative Edge Detection with Stable Diffusion [52.870631376660924]
  Edge detection is typically viewed as a pixel-level classification problem mainly addressed by discriminative methods. We propose a novel approach, named Generative Edge Detector (GED), by fully utilizing the potential of the pre-trained stable diffusion model. We conduct extensive experiments on multiple datasets and achieve competitive performance.
  arXiv  Detail & Related papers  (2024-10-04T01:52:23Z)
• Learning to utilize image second-order derivative information for crisp edge detection [13.848361661516595]
  Edge detection is a fundamental task in computer vision. Recent top-performing edge detection methods tend to generate thick and noisy edge lines. We propose a second-order derivative-based multi-scale contextual enhancement module (SDMCM) to help the model locate true edge pixels accurately. We also construct a hybrid focal loss function (HFL) to alleviate the imbalanced distribution issue. In the end, we propose a U-shape network named LUS-Net which is based on the SDMCM and BRM for edge detection.
  arXiv  Detail & Related papers  (2024-06-09T13:25:02Z)
• Automated Coastline Extraction Using Edge Detection Algorithms [2.5311562666866494]
  We analyse the effectiveness of edge detection algorithms for automatically extracting coastlines from satellite images. Four algorithms - Canny, Sobel, Scharr and Prewitt are compared visually and using metrics.
  arXiv  Detail & Related papers  (2024-05-19T09:25:55Z)
• DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection [20.278655159290302]
  We propose the first diffusion model for the task of general edge detection, which we call DiffusionEdge. To avoid expensive computational resources while retaining the final performance, we apply DPM in the latent space and enable the classic cross-entropy loss. With all the technical designs, DiffusionEdge can be stably trained with limited resources, predicting crisp and accurate edge maps with much fewer augmentation strategies.
  arXiv  Detail & Related papers  (2024-01-04T02:20:54Z)
• PNT-Edge: Towards Robust Edge Detection with Noisy Labels by Learning Pixel-level Noise Transitions [119.17602768128806]
  It is hard to manually label edges accurately, especially for large datasets. This paper proposes to learn Pixel-level NoiseTransitions to model the label-corruption process.
  arXiv  Detail & Related papers  (2023-07-26T09:45:17Z)
• Structure-Aware DropEdge Towards Deep Graph Convolutional Networks [83.38709956935095]
  Graph Convolutional Networks (GCNs) encounter a remarkable drop in performance when multiple layers are piled up. Over-smoothing isolates the network output from the input with the increase of network depth, weakening expressivity and trainability. We investigate refined measures upon DropEdge -- an existing simple yet effective technique to relieve over-smoothing.
  arXiv  Detail & Related papers  (2023-06-21T08:11:40Z)
• The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detector [70.43599299422813]
  Existing methods fuse multiple annotations using a simple voting process, ignoring the inherent ambiguity of edges and labeling bias of annotators. We propose a novel uncertainty-aware edge detector (UAED), which employs uncertainty to investigate the subjectivity and ambiguity of diverse annotations. UAED achieves superior performance consistently across multiple edge detection benchmarks.
  arXiv  Detail & Related papers  (2023-03-21T13:14:36Z)
• Anomalous Edge Detection in Edge Exchangeable Social Network Models [15.986251712074843]
  We exploit edge exchangeability as a criterion for distinguishing anomalous edges from normal edges. We present an anomaly detector based on conformal prediction theory.
  arXiv  Detail & Related papers  (2021-09-27T00:02:52Z)
• Unmixing Convolutional Features for Crisp Edge Detection [28.232800355331726]
  This paper presents a context-aware tracing strategy (CATS) for crisp edge detection with deep edge detectors. Experiments demonstrate that the proposed CATS can be integrated into modern deep edge detectors to improve localization accuracy.
  arXiv  Detail & Related papers  (2020-11-19T13:30:15Z)
• Dense Label Encoding for Boundary Discontinuity Free Rotation Detection [69.75559390700887]
  This paper explores a relatively less-studied methodology based on classification. We propose new techniques to push its frontier in two aspects. Experiments and visual analysis on large-scale public datasets for aerial images show the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-11-19T05:42:02Z)
• Refined Plane Segmentation for Cuboid-Shaped Objects by Leveraging Edge Detection [63.942632088208505]
  We propose a post-processing algorithm to align the segmented plane masks with edges detected in the image. This allows us to increase the accuracy of state-of-the-art approaches, while limiting ourselves to cuboid-shaped objects.
  arXiv  Detail & Related papers  (2020-03-28T18:51:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.