TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Unmixing Convolutional Features for Crisp Edge Detection

Unmixing Convolutional Features for Crisp Edge Detection

Linxi Huan, Nan Xue, Xianwei Zheng, wei he, Jianya Gong, Gui-Song Xia

2020-11-19Edge DetectionEdge Classification
PaperPDFCode(official)

Abstract

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. The CATS consists of two modules: a novel tracing loss that performs feature unmixing by tracing boundaries for better side edge learning, and a context-aware fusion block that tackles the side mixing by aggregating the complementary merits of learned side edges. Experiments demonstrate that the proposed CATS can be integrated into modern deep edge detectors to improve localization accuracy. With the vanilla VGG16 backbone, in terms of BSDS500 dataset, our CATS improves the F-measure (ODS) of the RCF and BDCN deep edge detectors by 12% and 6% respectively when evaluating without using the morphological non-maximal suppression scheme for edge detection.

Results

TaskDatasetMetricValueModel
Edge DetectionBIPEDODS0.887CATS
Edge DetectionMDBDODS0.891CATS
2D Object DetectionBIPEDODS0.887CATS
2D Object DetectionMDBDODS0.891CATS

Related Papers

DeepCS-TRD, a Deep Learning-based Cross-Section Tree Ring Detector2025-09-09U-R-VEDA: Integrating UNET, Residual Links, Edge and Dual Attention, and Vision Transformer for Accurate Semantic Segmentation of CMRs2025-06-25Mobile Image Analysis Application for Mantoux Skin Test2025-06-22Self-supervised Feature Extraction for Enhanced Ball Detection on Soccer Robots2025-06-20Exploring the Effectiveness of Deep Features from Domain-Specific Foundation Models in Retinal Image Synthesis2025-06-13Tropical Geometry Based Edge Detection Using Min-Plus and Max-Plus Algebra2025-05-24Hyb-KAN ViT: Hybrid Kolmogorov-Arnold Networks Augmented Vision Transformer2025-05-07Rethinking Boundary Detection in Deep Learning-Based Medical Image Segmentation2025-05-06