MEMO: Human-like Crisp Edge Detection Using Masked Edge Prediction

• URL: http://arxiv.org/abs/2603.20782v1
• Date: Sat, 21 Mar 2026 12:21:29 GMT
• Title: MEMO: Human-like Crisp Edge Detection Using Masked Edge Prediction
• Abstract summary: Masked Edge Prediction MOdel produces both accurate and crisp edges using only cross-entropy loss.<n>Key insight guiding our inference is that thick edge predictions typically exhibit a confidence gradient.<n>Our method achieves visually appealing, post-processing-free, human-like edge maps.
• Score: 45.91104326433983
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning-based edge detection models trained with cross-entropy loss often suffer from thick edge predictions, which deviate from the crisp, single-pixel annotations typically provided by humans. While previous approaches to achieving crisp edges have focused on designing specialized loss functions or modifying network architectures, we show that a carefully designed training and inference strategy alone is sufficient to achieve human-like edge quality. In this work, we introduce the Masked Edge Prediction MOdel (MEMO), which produces both accurate and crisp edges using only cross-entropy loss. We first construct a large-scale synthetic edge dataset to pre-train MEMO, enhancing its generalization ability. Subsequent fine-tuning on downstream datasets requires only a lightweight module comprising 1.2\% additional parameters. During training, MEMO learns to predict edges under varying ratios of input masking. A key insight guiding our inference is that thick edge predictions typically exhibit a confidence gradient: high in the center and lower toward the boundaries. Leveraging this, we propose a novel progressive prediction strategy that sequentially finalizes edge predictions in order of prediction confidence, resulting in thinner and more precise contours. Our method achieves visually appealing, post-processing-free, human-like edge maps and outperforms prior methods on crispness-aware evaluations.

Related papers

• Uncertainty-Guided Edge Learning for Deep Image Regression in Remote Sensing [25.426932126940432]
  We investigate edge learning in the context of performing deep image regression on a remote sensing satellite.<n>Underpinning UGEL is the calculation of predictive uncertainty based on deep beta regression.<n>Results show that UGEL delivers faster-converging edge learning than active or semi-supervised learning.
  arXiv  Detail & Related papers  (2026-05-07T02:17:17Z)
• MatchED: Crisp Edge Detection Using End-to-End, Matching-based Supervision [19.218741065333013]
  MethodLPP is a lightweight, only $sim$21K additional parameters and plug-and-play matching-based supervision module.<n>MethodLPP increases the Average Crispness (AC) metric by up to 2--4$times$ compared to baseline models.<n>MethodLPP achieves SOTA performance that matches or surpasses standard post-processing for the first time.
  arXiv  Detail & Related papers  (2026-02-24T08:45:49Z)
• EasyControlEdge: A Foundation-Model Fine-Tuning for Edge Detection [9.817969756082995]
  We propose EasyControlEdge, adapting an image-generation foundation model to edge detection.<n>We show consistent gains under no-post-processing crispness evaluation and with limited training data.
  arXiv  Detail & Related papers  (2026-02-18T07:28:09Z)
• MS2Edge: Towards Energy-Efficient and Crisp Edge Detection with Multi-Scale Residual Learning in SNNs [12.591111929378906]
  Edge detection with Artificial Neural Networks (ANNs) has achieved remarkable prog-ress but faces two major challenges.<n>It requires pre-training on large-scale extra data and complex designs for prior knowledge, leading to high energy consumption.<n>We build a novel spiking backbone named MS2ResNet that integrates multi-scale residual learning to recover missing boundary lines and generate crisp edges.
  arXiv  Detail & Related papers  (2025-11-05T15:56:46Z)
• 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 [16.152236524867078]
  Edge detection is a fundamental task in computer vision.<n>Recent top-performing edge detection methods tend to generate thick and noisy edge lines.<n>We propose a second-order derivative-based multi-scale contextual enhancement module (SDMCM) to help the model locate true edge pixels accurately.<n>We also construct a hybrid focal loss function (HFL) to alleviate the imbalanced distribution issue.<n>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)
• ADEdgeDrop: Adversarial Edge Dropping for Robust Graph Neural Networks [53.41164429486268]
  Graph Neural Networks (GNNs) have exhibited the powerful ability to gather graph-structured information from neighborhood nodes. The performance of GNNs is limited by poor generalization and fragile robustness caused by noisy and redundant graph data. We propose a novel adversarial edge-dropping method (ADEdgeDrop) that leverages an adversarial edge predictor guiding the removal of edges.
  arXiv  Detail & Related papers  (2024-03-14T08:31:39Z)
• Refined Edge Usage of Graph Neural Networks for Edge Prediction [51.06557652109059]
  We propose a novel edge prediction paradigm named Edge-aware Message PassIng neuRal nEtworks (EMPIRE) We first introduce an edge splitting technique to specify use of each edge where each edge is solely used as either the topology or the supervision. In order to emphasize the differences between pairs connected by supervision edges and pairs unconnected, we further weight the messages to highlight the relative ones that can reflect the differences.
  arXiv  Detail & Related papers  (2022-12-25T23:19:56Z)
• Learning to Predict Trustworthiness with Steep Slope Loss [69.40817968905495]
  We study the problem of predicting trustworthiness on real-world large-scale datasets. We observe that the trustworthiness predictors trained with prior-art loss functions are prone to view both correct predictions and incorrect predictions to be trustworthy. We propose a novel steep slope loss to separate the features w.r.t. correct predictions from the ones w.r.t. incorrect predictions by two slide-like curves that oppose each other.
  arXiv  Detail & Related papers  (2021-09-30T19:19:09Z)
• DeepStrip: High Resolution Boundary Refinement [60.00241966809684]
  We propose to convert regions of interest into strip images and compute a boundary prediction in the strip domain. To detect the target boundary, we present a framework with two prediction layers. We enforce a matching consistency and C0 continuity regularization to the network to reduce false alarms.
  arXiv  Detail & Related papers  (2020-03-25T22:44:48Z)

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.