mlsanityData to 7 Oct 2026

Optimizing Edge Detection for Image Segmentation with Multicut Penalties

arXiv 2112.05416 ↗First posted 10 Dec 2021cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

The Minimum Cost Multicut Problem (MP) is a popular way for obtaining a graph decomposition by optimizing binary edge labels over edge costs. While the formulation of a MP from independently estimated costs per edge is highly flexible and intuitive, solving the MP is NP-hard and time-expensive. As a remedy, recent work proposed to predict edge probabilities with awareness to potential conflicts by incorporating cycle constraints in the prediction process. We argue that such formulation, while providing a first step towards end-to-end learnable edge weights, is suboptimal, since it is built upon a loose relaxation of the MP. We therefore propose an adaptive CRF that allows to progressively consider more violated constraints and, in consequence, to issue solutions with higher validity. Experiments on the BSDS500 benchmark for natural image segmentation as well as on electron microscopic recordings show that our approach yields more precise edge detection and image segmentation.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 14 of its 42 references that are in the map. First posted on arXiv 10 Dec 2021.

Builds on

14 of 42 references.

References · 14

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,182
  4. 2015Holistically-Nested Edge Detectioncited by 590
  5. 2015Conditional Random Fields as Recurrent Neural Networkscited by 213
  6. 2016UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memorycited by 200
  7. 2016Richer Convolutional Features for Edge Detectioncited by 141
  8. 2015Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generationcited by 90
  9. 2019Understanding Deep Learning Techniques for Image Segmentationcited by 38
  10. 2015Efficient Decomposition of Image and Mesh Graphs by Lifted Multicutscited by 26
  11. 2017Automatic Breast Ultrasound Image Segmentation: A Surveycited by 15
  12. 2016A Message Passing Algorithm for the Minimum Cost Multicut Problemcited by 11
2 more
  1. 2013Higher-order Segmentation via Multicutscited by 7
  2. 2018End-to-end Learning for Graph Decompositioncited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 1; 2025: 0; 2026: 1.

4 papers.

  1. 2023CosPGD: an efficient white-box adversarial attack for pixel-wise prediction taskscited by 27
  2. 2022Learning to solve Minimum Cost Multicuts efficiently using Edge-Weighted Graph Convolutional Neural Networkscited by 5
  3. 2024I Spy With My Little Eye: A Minimum Cost Multicut Investigation of Dataset Framescited by 3
  4. 2026ClimateVID -- Social Media Videos Analysis and Challenges Involvedcited by 0