mlsanityData to 14 Oct 2026

Tiny and Efficient Model for the Edge Detection Generalization

arXiv 2308.06468 ↗First posted 12 Aug 2023cs.CV cs.LGcited by 28

Not on the map. Why?

Abstract (arXiv)

Most high-level computer vision tasks rely on low-level image operations as their initial processes. Operations such as edge detection, image enhancement, and super-resolution, provide the foundations for higher level image analysis. In this work we address the edge detection considering three main objectives: simplicity, efficiency, and generalization since current state-of-the-art (SOTA) edge detection models are increased in complexity for better accuracy. To achieve this, we present Tiny and Efficient Edge Detector (TEED), a light convolutional neural network with only 58K parameters, less than 0.2% of the state-of-the-art models. Training on the BIPED dataset takes less than 30 minutes, with each epoch requiring less than 5 minutes. Our proposed model is easy to train and it quickly converges within very first few epochs, while the predicted edge-maps are crisp and of high quality. Additionally, we propose a new dataset to test the generalization of edge detection, which comprises samples from popular images used in edge detection and image segmentation. The source code is available in https://github.com/xavysp/TEED.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Builds on 25 of its 56 references that are in the map. First posted on arXiv 12 Aug 2023.

Builds on

25 of 56 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  7. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  8. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,069
  9. 2021Transformers in Vision: A Surveycited by 1,013
  10. 2021Scaling Vision Transformerscited by 999
  11. 2015Holistically-Nested Edge Detectioncited by 592
  12. 2021Pixel Difference Networks for Efficient Edge Detectioncited by 168
13 more
  1. 2018Deep Learning for Single Image Super-Resolution: A Brief Reviewcited by 158
  2. 2016Richer Convolutional Features for Edge Detectioncited by 143
  3. 2019Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detectioncited by 104
  4. 2018Learning to predict crisp boundariescited by 82
  5. 2020Learning to Parse Wireframes in Images of Man-Made Environmentscited by 71
  6. 2021Dense Extreme Inception Network for Edge Detectioncited by 39
  7. 2018PIRM Challenge on Perceptual Image Enhancement on Smartphones: Reportcited by 38
  8. 2019Depthwise Convolution is All You Need for Learning Multiple Visual Domainscited by 36
  9. 2022EDTER: Edge Detection with Transformercited by 36
  10. 2021RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depthcited by 33
  11. 2020Unmixing Convolutional Features for Crisp Edge Detectioncited by 32
  12. 2020Traditional Method Inspired Deep Neural Network for Edge Detectioncited by 6
  13. 2018Quality assessment metrics for edge detection and edge-aware filtering: A tutorial reviewcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 14; 2026: 8.

28 papers.

Sort:

By area:

  1. 2024PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructionscited by 31
  2. 2024MagicQuill: An Intelligent Interactive Image Editing Systemcited by 30
  3. 2024KALIE: Fine-Tuning Vision-Language Models for Open-World Manipulation without Robot Datacited by 15
  4. 2025Point2RBox-v2: Rethinking Point-supervised Oriented Object Detection with Spatial Layout Among Instancescited by 11
  5. 2025ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframingcited by 8
  6. 2025MagicQuillV2: Precise and Interactive Image Editing with Layered Visual Cuescited by 4
  7. 2025MixSA: Training-free Reference-based Sketch Extraction via Mixture-of-Self-Attentioncited by 3
  8. 2025Boosting Edge Detection with Pixel-wise Feature Selection: The Extractor-Selector Paradigmcited by 3
  9. 2025MonoMVSNet: Monocular Priors Guided Multi-View Stereo Networkcited by 3
  10. 2024SuperEdge: Towards a Generalization Model for Self-Supervised Edge Detectioncited by 2
  11. 2024A Comprehensive Study for Edge Detection: Ideal-Prior Guidance Learning, High-Precision Architecture, and Better Distinguishability Evaluation Benchmarkcited by 2
  12. 2025Symmetrization Weighted Binary Cross-Entropy: Modeling Perceptual Asymmetry for Human-Consistent Neural Edge Detectioncited by 2
16 more
  1. 2025DeepTopoNet: A Framework for Subglacial Topography Estimation on the Greenland Ice Sheetscited by 2
  2. 2025Multi-Scale Tensorial Summation and Dimensional Reduction Guided Neural Network for Edge Detectioncited by 1
  3. 2025GeomHair: Reconstruction of Hair Strands from Colorless 3D Scanscited by 1
  4. 2025Binarization-Aware Adjuster for Discrete Decision Learning with an Application to Edge Detectioncited by 1
  5. 2025Structure-Guided Diffusion Models for High-Fidelity Portrait Shadow Removalcited by 1
  6. 2025Stroke2Sketch: Harnessing Stroke Attributes for Training-Free Sketch Generationcited by 1
  7. 2026MatchED: Crisp Edge Detection Using End-to-End, Matching-based Supervisioncited by 1
  8. 2024Hybrid Primal Sketch: Combining Analogy, Qualitative Representations, and Computer Vision for Scene Understandingcited by 0
  9. 2025Edge-Boundary-Texture Loss: A Tri-Class Generalization of Weighted Binary Cross-Entropy for Enhanced Edge Detectioncited by 0
  10. 2026MooneyMaker: A Python package to create ambiguous two-tone imagescited by 0
  11. 2026Sketch It Out: Exploring Label-Free Structural Cues for Multimodal Gait Recognitioncited by 0
  12. 2026Quantum Gradient-Based Approach for Edge and Corner Detection Using Sobel Kernelscited by 0
  13. 2026Hidden-Shot: Towards One-Shot Task Generalization for Low-Level Vision Generalist Modelscited by 0
  14. 2026Neighbor-Aware View Synthesis for Restoring Missing Views in Light-Field Camera Arrayscited by 0
  15. 2026RealOOB: A Definition-Consistent Real-World Oriented Occlusion Boundary Benchmarkcited by 0
  16. 2026OmniVBench: A Benchmark and Large-Scale Dataset for Omni Reference-to-Video Generationcited by 0