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

• URL: http://arxiv.org/abs/2303.11828v1
• Date: Tue, 21 Mar 2023 13:14:36 GMT
• Title: The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detector
• Authors: Caixia Zhou and Yaping Huang and Mengyang Pu and Qingji Guan and Li Huang and Haibin Ling
• Abstract summary: 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.
• Score: 70.43599299422813
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 \url{https://github.com/ZhouCX117/UAED}

Related papers

• 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)
• ED$^4$: Explicit Data-level Debiasing for Deepfake Detection [24.695989108814018]
  Learning intrinsic bias from limited data has been considered the main reason for the failure of deepfake detection with generalizability. We present ED$4$, a simple and effective strategy to address aforementioned biases explicitly at the data level. We conduct extensive experiments to demonstrate its effectiveness and superiority over existing deepfake detection approaches.
  arXiv  Detail & Related papers  (2024-08-13T10:05:20Z)
• Graph Anomaly Detection with Noisy Labels by Reinforcement Learning [13.135788402192215]
  We propose a novel framework REGAD, i.e., REinforced Graph Anomaly Detector. Specifically, we aim to maximize the performance improvement (AUC) of a base detector by cutting noisy edges approximated through the nodes with high-confidence labels.
  arXiv  Detail & Related papers  (2024-07-08T13:41:21Z)
• Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection [57.646582245834324]
  We propose a simple yet effective deepfake detector called LSDA. It is based on a idea: representations with a wider variety of forgeries should be able to learn a more generalizable decision boundary. We show that our proposed method is surprisingly effective and transcends state-of-the-art detectors across several widely used benchmarks.
  arXiv  Detail & Related papers  (2023-11-19T09:41:10Z)
• Don't Miss Out on Novelty: Importance of Novel Features for Deep Anomaly Detection [64.21963650519312]
  Anomaly Detection (AD) is a critical task that involves identifying observations that do not conform to a learned model of normality. We propose a novel approach to AD using explainability to capture such novel features as unexplained observations in the input space. Our approach establishes a new state-of-the-art across multiple benchmarks, handling diverse anomaly types.
  arXiv  Detail & Related papers  (2023-10-01T21:24:05Z)
• GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation [70.75100533512021]
  In this paper, we formulate the label uncertainty problem as the diversity of potentially plausible bounding boxes of objects. We propose GLENet, a generative framework adapted from conditional variational autoencoders, to model the one-to-many relationship between a typical 3D object and its potential ground-truth bounding boxes with latent variables. The label uncertainty generated by GLENet is a plug-and-play module and can be conveniently integrated into existing deep 3D detectors.
  arXiv  Detail & Related papers  (2022-07-06T06:26:17Z)
• Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection [66.10057490293981]
  We propose a data-uncertainty guided multi-phase learning method for semi-supervised object detection. Our method behaves extraordinarily compared to baseline approaches and outperforms them by a large margin.
  arXiv  Detail & Related papers  (2021-03-29T09:27:23Z)
• Pixel-wise Anomaly Detection in Complex Driving Scenes [30.884375526254836]
  We present a pixel-wise anomaly detection framework that uses uncertainty maps to improve anomaly detection. Our approach works as a general framework around already trained segmentation networks. Top-2 performance across a range of different anomaly datasets shows the robustness of our approach to handling different anomaly instances.
  arXiv  Detail & Related papers  (2021-03-09T14:26:20Z)

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.