# A Visually Attentive Splice Localization Network with Multi-Domain Feature Extractor and Multi-Receptive Field Upsampler

arXiv: https://arxiv.org/abs/2401.06995 · HTML: https://mlsanity.com/paper/2401.06995/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 16 references that are in the map.
- First posted on arXiv 13 Jan 2024.

## Builds on (most cited first, 5 of 5)

- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Image Manipulation Detection by Multi-View Multi-Scale Supervision](https://mlsanity.com/paper/2104.06832/) (2021)
- [Rotate to Attend: Convolutional Triplet Attention Module](https://mlsanity.com/paper/2010.03045/) (2020)
- [Localization of JPEG double compression through multi-domain convolutional neural networks](https://mlsanity.com/paper/1706.01788/) (2017)
- [Deep Multi-scale Discriminative Networks for Double JPEG Compression Forensics](https://mlsanity.com/paper/1904.02520/) (2019)

## Built on by (most cited first, 1 of 1)

- [VAAS: Vision-Attention Anomaly Scoring for Image Manipulation Detection in Digital Forensics](https://mlsanity.com/paper/2512.15512/) (2025)

## Abstract (arXiv)

Image splice manipulation presents a severe challenge in today's society. With easy access to image manipulation tools, it is easier than ever to modify images that can mislead individuals, organizations or society. In this work, a novel, "Visually Attentive Splice Localization Network with Multi-Domain Feature Extractor and Multi-Receptive Field Upsampler" has been proposed. It contains a unique "visually attentive multi-domain feature extractor" (VA-MDFE) that extracts attentional features from the RGB, edge and depth domains. Next, a "visually attentive downsampler" (VA-DS) is responsible for fusing and downsampling the multi-domain features. Finally, a novel "visually attentive multi-receptive field upsampler" (VA-MRFU) module employs multiple receptive field-based convolutions to upsample attentional features by focussing on different information scales. Experimental results conducted on the public benchmark dataset CASIA v2.0 prove the potency of the proposed model. It comfortably beats the existing state-of-the-arts by achieving an IoU score of 0.851, pixel F1 score of 0.9195 and pixel AUC score of 0.8989.