The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detector

by   Caixia Zhou, et al.
Stony Brook University
North China Electric Power University

Deep learning-based edge detectors heavily rely on pixel-wise labels which are often provided by multiple annotators. Existing methods fuse multiple annotations using a simple voting process, ignoring the inherent ambiguity of edges and labeling bias of annotators. In this paper, we propose a novel uncertainty-aware edge detector (UAED), which employs uncertainty to investigate the subjectivity and ambiguity of diverse annotations. Specifically, we first convert the deterministic label space into a learnable Gaussian distribution, whose variance measures the degree of ambiguity among different annotations. Then we regard the learned variance as the estimated uncertainty of the predicted edge maps, and pixels with higher uncertainty are likely to be hard samples for edge detection. Therefore we design an adaptive weighting loss to emphasize the learning from those pixels with high uncertainty, which helps the network to gradually concentrate on the important pixels. UAED can be combined with various encoder-decoder backbones, and the extensive experiments demonstrate that UAED achieves superior performance consistently across multiple edge detection benchmarks. The source code is available at <>


page 1

page 7


Hypernet-Ensemble Learning of Segmentation Probability for Medical Image Segmentation with Ambiguous Labels

Despite the superior performance of Deep Learning (DL) on numerous segme...

Pixel-wise Dense Detector for Image Inpainting

Recent GAN-based image inpainting approaches adopt an average strategy t...

EddyNet: A Deep Neural Network For Pixel-Wise Classification of Oceanic Eddies

This work presents EddyNet, a deep learning based architecture for autom...

Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation

Surface normal estimation from a single image is an important task in 3D...

STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection

Recently, deep learning-based facial landmark detection has achieved sig...

Uncertainty-aware INVASE: Enhanced Breast Cancer Diagnosis Feature Selection

In this paper, we present an uncertainty-aware INVASE to quantify predic...

Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation

To generate "accurate" scene graphs, almost all existing methods predict...

Please sign up or login with your details

Forgot password? Click here to reset