CoChat

Hierarchical Fine-Grained Image Forgery Detection and Localization

Open access
Guo, Xiao, Liu, Xiaohong, Ren, Zhiyuan, Grosz, Steven, Masi, Iacopo, Liu, Xiaoming · 2023 · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Cited by 205

The DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.

Abstract

Differences in forgery attributes of images generated in CNN-synthesized and image-editing domains are large, and such differences make a unified image forgery detection and localization (IFDL) challenging. To this end, we present a hierarchical fine-grained formulation for IFDL representation learning. Specifically, we first represent forgery attributes of a manipulated image with multiple labels at different levels. Then we perform fine-grained classification at these levels using the hierarchical dependency between them. As a result, the algorithm is encouraged to learn both comprehensive features and inherent hierarchical nature of different forgery attributes, thereby improving the IFDL representation. Our proposed IFDL framework contains three components: multi-branch feature extractor, localization and classification modules. Each branch of the feature extractor learns to classify forgery attributes at one level, while localization and classification modules segment the pixel-level forgery region and detect image-level forgery, respectively. Lastly, we construct a hierarchical fine-grained dataset to facilitate our study. We demonstrate the effectiveness of our method on 7 different benchmarks, for both tasks of IFDL and forgery attribute classification. Our source code and dataset can be found: github.com/CHELSEA234/HiFi-IFDL.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr52729.2023.00308

Cites

35 of 35 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 35 references

Research works printed but not linked: 42

  1. ruff, 2018, Deep one-class classification, ICML
  2. 10.1109/FG57933.2023.10042500 · DOI · Paper page
  3. 10.1007/978-981-16-7621-5 · DOI
  4. 10.1109/ACCESS.2019.2899367 · DOI · Paper page
  5. ricker, 2022, Towards the detection of diffusion model deepfakes, ArXiv Preprint
  6. 10.1109/ICCV48922.2021.01392 · DOI · Paper page
  7. 10.1109/TPAMI.2022.3180556 · DOI · Paper page
  8. dufour, 2019, Deepfakes detection dataset by google & jigsaw
  9. 10.1109/ChinaSIP.2013.6625374 · DOI · Paper page
  10. 10.1145/882262.882269 · DOI · Paper page
  11. 10.1109/WACVW50321.2020.9096940 · DOI · Paper page
  12. ng, 2009, Columbia image splicing detection evaluation dataset, DVMM lab Columbia Univ CalPhotos Digit Libr
  13. 10.1109/ICASSP.2018.8462585 · DOI · Paper page
  14. 10.1109/TCSVT.2022.3189545 · DOI · Paper page
  15. 10.1007/978-3-031-19781-9_9 · DOI
  16. 10.1109/CVPR52729.2023.01188 · DOI
  17. 10.1016/B978-0-08-051581-6.50065-9 · DOI · Paper page
  18. 10.1001/jamanetworkopen.2020.22199 · DOI
  19. 2022, Infodemic-world Health Organization
  20. asnani, 2021, Reverse engineering of generative models: Inferring model hyperparameters from generated images, ArXiv Preprint
  21. 10.1109/CVPR52688.2022.01495 · DOI
  22. lin, 2014, Microsoft coco: Common objects in context, ECCV
  23. 10.1007/s11263-022-01617-5 · DOI · Paper page
  24. 10.1109/CVPR42600.2020.00559 · DOI · Paper page
  25. karras, 2021, Alias-free generative adversarial networks, NeurIPS
  26. 10.1609/aaai.v34i07.7007 · DOI · Paper page
  27. kingma, 2014, Auto-encoding variational bayes, ICLRE
  28. 10.1109/CVPR.2018.00116 · DOI · Paper page
  29. 2016, NIST Nist Nimble 2016 Datasets
  30. 0, Survey More americans get news from internet than newspapers or radio
  31. li, 2022, Image-to-image translation via hierarchical style disentanglement, CVPR
  32. 10.1109/ICCV.2019.00765 · DOI · Paper page
  33. yu, 2015, Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop, ArXiv Preprint
  34. 10.1109/CVPR.2019.00977 · DOI · Paper page
  35. 10.1007/978-3-030-01231-1_11 · DOI · Paper page
  36. hu, 2020, Span: spatial pyramid attention network for image manipulation localization, ECCV
  37. hsu, 2021, Discourse-level relation extraction via graph pooling, AAAI DLG Wrokshop
  38. 10.1109/CVPR52688.2022.01308 · DOI · Paper page
  39. 10.1609/aaai.v33i01.33012580 · DOI
  40. 10.1109/CVPR52688.2022.00240 · DOI · Paper page
  41. guo, 2020, Cord19sts: Covid19 semantic textual similarity dataset, ArXiv Preprint
  42. guo, 2022, Multidomain learning for updating face anti-spoofing models, ECCV

Cited by

Metadata

Authors
Guo, X., Liu, X., Ren, Z., Grosz, S., Masi, I., & Liu, X.
Venue
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2023-06
Pages
3155-3165
ISSN
1063-6919 (ISSN-L)
OpenAlex
W4386075856
Cited by
205
References
35
FWCI
23.31
Type
conference paper
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.