mlsanityData to 7 Oct 2026

Inharmonious Region Localization by Magnifying Domain Discrepancy

arXiv 2209.15368 ↗First posted 30 Sep 2022cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Inharmonious region localization aims to localize the region in a synthetic image which is incompatible with surrounding background. The inharmony issue is mainly attributed to the color and illumination inconsistency produced by image editing techniques. In this work, we tend to transform the input image to another color space to magnify the domain discrepancy between inharmonious region and background, so that the model can identify the inharmonious region more easily. To this end, we present a novel framework consisting of a color mapping module and an inharmonious region localization network, in which the former is equipped with a novel domain discrepancy magnification loss and the latter could be an arbitrary localization network. Extensive experiments on image harmonization dataset show the superiority of our designed framework. Our code is available at https://github.com/bcmi/MadisNet-Inharmonious-Region-Localization.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 30 of its 49 references that are in the map. First posted on arXiv 30 Sep 2022.

Builds on

30 of 49 references.

References · 30

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  6. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  7. 2018Self-Attention Generative Adversarial Networkscited by 809
  8. 2020Zero-Reference Deep Curve Estimation for Low-Light Image Enhancementcited by 541
  9. 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505
  10. 2020Multi-scale Interactive Network for Salient Object Detectioncited by 212
  11. 2017Deep Bilateral Learning for Real-Time Image Enhancementcited by 200
  12. 2020Searching Central Difference Convolutional Networks for Face Anti-Spoofingcited by 173
18 more
  1. 2021StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generatorscited by 164
  2. 2020Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-timecited by 163
  3. 2018Fighting Fake News: Image Splice Detection via Learned Self-Consistencycited by 136
  4. 2019DoveNet: Deep Image Harmonization via Domain Verificationcited by 134
  5. 2020Suppress and Balance: A Simple Gated Network for Salient Object Detectioncited by 126
  6. 2017Deep Image Harmonizationcited by 120
  7. 2020SPAN: Spatial Pyramid Attention Network forImage Manipulation Localizationcited by 92
  8. 2019Improving the Harmony of the Composite Image by Spatial-Separated Attention Modulecited by 73
  9. 2021Region-aware Adaptive Instance Normalization for Image Harmonizationcited by 71
  10. 2017Image Splicing Localization Using A Multi-Task Fully Convolutional Network (MFCN)cited by 64
  11. 2019Hybrid LSTM and Encoder-Decoder Architecture for Detection of Image Forgeriescited by 59
  12. 2020Foreground-aware Semantic Representations for Image Harmonizationcited by 53
  13. 2020BargainNet: Background-Guided Domain Translation for Image Harmonizationcited by 52
  14. 2021TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformationscited by 48
  15. 2018Generate, Segment and Refine: Towards Generic Manipulation Segmentationcited by 33
  16. 2020Joint Bilateral Learning for Real-time Universal Photorealistic Style Transfercited by 31
  17. 2019Constrained R-CNN: A general image manipulation detection modelcited by 29
  18. 2021Inharmonious Region Localizationcited by 5

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1.

2 papers.