SImProv: Scalable Image Provenance Framework for Robust Content Attribution
Not on the map. Why?
Abstract (arXiv)
We present SImProv - a scalable image provenance framework to match a query image back to a trusted database of originals and identify possible manipulations on the query. SImProv consists of three stages: a scalable search stage for retrieving top-k most similar images; a re-ranking and near-duplicated detection stage for identifying the original among the candidates; and finally a manipulation detection and visualization stage for localizing regions within the query that may have been manipulated to differ from the original. SImProv is robust to benign image transformations that commonly occur during online redistribution, such as artifacts due to noise and recompression degradation, as well as out-of-place transformations due to image padding, warping, and changes in size and shape. Robustness towards out-of-place transformations is achieved via the end-to-end training of a differentiable warping module within the comparator architecture. We demonstrate effective retrieval and manipulation detection over a dataset of 100 million images.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 22 of its 48 references that are in the map. First posted on arXiv 28 Jun 2022.
Builds on
22 of 48 references.
References · 22
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
- 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
- 2017Billion-scale similarity search with GPUscited by 2,497
- 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
- 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
- 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,101
- 2019CNN-generated images are surprisingly easy to spot... for nowcited by 847
- 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 499
- 2015Particular object retrieval with integral max-pooling of CNN activationscited by 161
- 2016Deep Image Retrieval: Learning global representations for image searchcited by 147
- 2018Fighting Fake News: Image Splice Detection via Learned Self-Consistencycited by 136
10 more
- 2017HashNet: Deep Learning to Hash by Continuationcited by 122
- 2019Deep Learning for Deepfakes Creation and Detection: A Surveycited by 102
- 2019Central Similarity Quantization for Efficient Image and Video Retrievalcited by 77
- 2019Detecting Photoshopped Faces by Scripting Photoshopcited by 55
- 2021The 2021 Image Similarity Dataset and Challengecited by 44
- 2018Self-Supervised Feature Learning by Learning to Spot Artifactscited by 43
- 2017Deep Supervised Discrete Hashingcited by 36
- 2014Hashing for Similarity Search: A Surveycited by 34
- 2018The PS-Battles Dataset - an Image Collection for Image Manipulation Detectioncited by 16
- 2018ARCHANGEL: Trusted Archives of Digital Public Documentscited by 7
Built on by
Citing papers per year: 2026: 1.
1 paper.