SPAN: Spatial Pyramid Attention Network forImage Manipulation Localization
Not on the map. Why?
Abstract (arXiv)
We present a novel framework, Spatial Pyramid Attention Network (SPAN) for detection and localization of multiple types of image manipulations. The proposed architecture efficiently and effectively models the relationship between image patches at multiple scales by constructing a pyramid of local self-attention blocks. The design includes a novel position projection to encode the spatial positions of the patches. SPAN is trained on a generic, synthetic dataset but can also be fine tuned for specific datasets; The proposed method shows significant gains in performance on standard datasets over previous state-of-the-art methods.
Key facts. Cited by 92 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Sep 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 11; 2022: 19; 2023: 19; 2024: 19; 2025: 16; 2026: 8.
92 papers.
Sort:
By area:
- 2023Hierarchical Fine-Grained Image Forgery Detection and Localizationcited by 134
- 2021PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localizationcited by 133
- 2022TruFor: Leveraging all-round clues for trustworthy image forgery detection and localizationcited by 130
- 2021MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detectioncited by 117
- 2023Explicit Visual Prompting for Low-Level Structure Segmentationscited by 113
- 2021Image Manipulation Detection by Multi-View Multi-Scale Supervisioncited by 111
- 2024FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Modelscited by 111
- 2023EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protectioncited by 109
- 2021Learning JPEG Compression Artifacts for Image Manipulation Detection and Localizationcited by 78
- 2022ObjectFormer for Image Manipulation Detection and Localizationcited by 78
- 2021Making Images Real Again: A Comprehensive Survey on Deep Image Compositioncited by 63
- 2023IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformercited by 42
38 more
- 2024IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localizationcited by 42
- 2022Visual Attention Methods in Deep Learning: An In-Depth Surveycited by 37
- 2024Mesoscopic Insights: Orchestrating Multi-scale & Hybrid Architecture for Image Manipulation Localizationcited by 35
- 2023Pixel-Inconsistency Modeling for Image Manipulation Localizationcited by 33
- 2021TransForensics: Image Forgery Localization with Dense Self-Attentioncited by 26
- 2021Self-Adversarial Training incorporating Forgery Attention for Image Forgery Localizationcited by 24
- 2023Weakly-supervised deepfake localization in diffusion-generated imagescited by 24
- 2023Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learningcited by 23
- 2023Pre-training-free Image Manipulation Localization through Non-Mutually Exclusive Contrastive Learningcited by 23
- 2023Rethinking Image Editing Detection in the Era of Generative AI Revolutioncited by 21
- 2024TGIF: Text-Guided Inpainting Forgery Datasetcited by 20
- 2022Learning to Immunize Images for Tamper Localization and Self-Recoverycited by 19
- 2024GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localizationcited by 19
- 2023Explicit Visual Prompting for Universal Foreground Segmentationscited by 17
- 2024DeCLIP: Decoding CLIP representations for deepfake localizationcited by 17
- 2024Language-guided Hierarchical Fine-grained Image Forgery Detection and Localizationcited by 16
- 2021Thermal Infrared Image Colorization for Nighttime Driving Scenes with Top-Down Guided Attentioncited by 15
- 2024Exploring Multi-view Pixel Contrast for General and Robust Image Forgery Localizationcited by 15
- 2022CFL-Net: Image Forgery Localization Using Contrastive Learningcited by 12
- 2024FlexEdit: Flexible and Controllable Diffusion-based Object-centric Image Editingcited by 12
- 2021GCA-Net : Utilizing Gated Context Attention for Improving Image Forgery Localization and Detectioncited by 11
- 2024ForgeryGPT: A Multimodal LLM for Interpretable Image Forgery Detection and Localizationcited by 11
- 2024ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detectioncited by 11
- 2023DRAW: Defending Camera-shooted RAW against Image Manipulationcited by 10
- 2022Comprint: Image Forgery Detection and Localization using Compression Fingerprintscited by 9
- 2022VideoFACT: Detecting Video Forgeries Using Attention, Scene Context, and Forensic Tracescited by 9
- 2022Towards Effective Image Manipulation Detection with Proposal Contrastive Learningcited by 8
- 2023TBFormer: Two-Branch Transformer for Image Forgery Localizationcited by 8
- 2023A New Benchmark and Model for Challenging Image Manipulation Detectioncited by 8
- 2024ForgeryTTT: Zero-Shot Image Manipulation Localization with Test-Time Trainingcited by 8
- 2021DSNet: A Dual-Stream Framework for Weakly-Supervised Gigapixel Pathology Image Analysiscited by 7
- 2024Fusion Transformer with Object Mask Guidance for Image Forgery Analysiscited by 7
- 2025M2SFormer: Multi-Spectral and Multi-Scale Attention with Edge-Aware Difficulty Guidance for Image Forgery Localizationcited by 6
- 2025ForensicsSAM: Toward Robust and Unified Image Forgery Detection and Localization Resisting to Adversarial Attackcited by 6
- 2022ReLoc: A Restoration-Assisted Framework for Robust Image Tampering Localizationcited by 5
- 2023TrainFors: A Large Benchmark Training Dataset for Image Manipulation Detection and Localizationcited by 5
- 2023MMFusion: Combining Image Forensic Filters for Visual Manipulation Detection and Localizationcited by 5
- 2023Pyramid Pixel Context Adaption Network for Medical Image Classification with Supervised Contrastive Learningcited by 4
50 most cited of 92 All 92 (JSON)
- 2026GIFTBench: Diagnosing Generalization in Image Forgery Localization and Informing Model Design1 Oct 2026
- 2026GAP-SAM: A Global Artifact Prior for Generalizable AI-Generated Image Manipulation Localization21 Aug 2026
- 2026SARIF: Segment Anything for Robust Image Forensics19 Jun 2026
- 2026Multi-axis Analysis of Image Manipulation Localization19 May 2026
- 2026Towards Generalized Image Manipulation Localization via Score-based Model16 May 2026
- 2026Off-the-shelf Vision Models Benefit Image Manipulation Localization10 Apr 2026
- 2026DiffFace-Edit: A Diffusion-Based Facial Dataset for Forgery-Semantic Driven Deepfake Detection Analysis20 Jan 2026
- 2026Shallow- and Deep-fake Image Manipulation Localization Using Vision Mamba and Guided Graph Neural Network5 Jan 2026
- 2025NeXT-IMDL: Build Benchmark for NeXT-Generation Image Manipulation Detection & Localization29 Dec 2025
- 2025Creating Blank Canvas Against AI-enabled Image Forgery27 Nov 2025
- 2025Unlocking the Forgery Detection Potential of Vanilla MLLMs: A Novel Training-Free Pipeline17 Nov 2025
- 2025StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models22 Sep 2025
38 more
- 2025Morphology-optimized Multi-Scale Fusion: Combining Local Artifacts and Mesoscopic Semantics for Deepfake Detection and Localization17 Sep 2025
- 2025Webly-Supervised Image Manipulation Localization via Category-Aware Auto-Annotation28 Aug 2025
- 2025Propose and Rectify: A Forensics-Driven MLLM Framework for Image Manipulation Localization25 Aug 2025
- 2025ForensicsSAM: Toward Robust and Unified Image Forgery Detection and Localization Resisting to Adversarial Attack10 Aug 2025
- 2025UGD-IML: A Unified Generative Diffusion-based Framework for Constrained and Unconstrained Image Manipulation Localization8 Aug 2025
- 2025AttZoom: Attention Zoom for Better Visual Features5 Aug 2025
- 2025Weakly-Supervised Image Forgery Localization via Vision-Language Collaborative Reasoning Framework2 Aug 2025
- 2025SAMwave: Wavelet-Driven Feature Enrichment for Effective Adaptation of Segment Anything Model27 Jul 2025
- 2025M2SFormer: Multi-Spectral and Multi-Scale Attention with Edge-Aware Difficulty Guidance for Image Forgery Localization26 Jun 2025
- 2025WebGuard++:Interpretable Malicious URL Detection via Bidirectional Fusion of HTML Subgraphs and Multi-Scale Convolutional BERT24 Jun 2025
- 2025Reinforced Multi-teacher Knowledge Distillation for Efficient General Image Forgery Detection and Localization7 Apr 2025
- 2025HRR: Hierarchical Retrospection Refinement for Generated Image Detection25 Feb 2025
- 2024Mesoscopic Insights: Orchestrating Multi-scale & Hybrid Architecture for Image Manipulation Localization18 Dec 2024
- 2024ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detection29 Nov 2024
- 2024Image Forgery Localization via Guided Noise and Multi-Scale Feature Aggregation17 Nov 2024
- 2024Language-guided Hierarchical Fine-grained Image Forgery Detection and Localization31 Oct 2024
- 2024ForgeryGPT: A Multimodal LLM for Interpretable Image Forgery Detection and Localization14 Oct 2024
- 2024ForgeryTTT: Zero-Shot Image Manipulation Localization with Test-Time Training5 Oct 2024
- 2024FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models3 Oct 2024
- 2024DeCLIP: Decoding CLIP representations for deepfake localization12 Sep 2024
- 2024A Noise and Edge extraction-based dual-branch method for Shallowfake and Deepfake Localization2 Sep 2024
- 2024FastForensics: Efficient Two-Stream Design for Real-Time Image Manipulation Detection29 Aug 2024
- 2024TGIF: Text-Guided Inpainting Forgery Dataset16 Jul 2024
- 2024M^3:Manipulation Mask Manufacturer for Arbitrary-Scale Super-Resolution Mask4 Jul 2024
- 2024GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localization24 Jun 2024
- 2024Exploring Multi-view Pixel Contrast for General and Robust Image Forgery Localization19 Jun 2024
- 2024IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization15 Jun 2024
- 2024MALT: Multi-scale Action Learning Transformer for Online Action Detection31 May 2024
- 2024FlexEdit: Flexible and Controllable Diffusion-based Object-centric Image Editing27 Mar 2024
- 2024Fusion Transformer with Object Mask Guidance for Image Forgery Analysis18 Mar 2024
- 2024PROMPT-IML: Image Manipulation Localization with Pre-trained Foundation Models Through Prompt Tuning1 Jan 2024
- 2023EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protection12 Dec 2023
- 2023MMFusion: Combining Image Forensic Filters for Visual Manipulation Detection and Localization4 Dec 2023
- 2023Rethinking Image Editing Detection in the Era of Generative AI Revolution29 Nov 2023
- 2023A New Benchmark and Model for Challenging Image Manipulation Detection23 Nov 2023
- 2023Progressive Feedback-Enhanced Transformer for Image Forgery Localization15 Nov 2023
- 2023Weakly-supervised deepfake localization in diffusion-generated images8 Nov 2023
- 2023Evading Detection Actively: Toward Anti-Forensics against Forgery Localization16 Oct 2023
50 newest of 92 All 92 (JSON)
- 2023Weakly-supervised deepfake localization in diffusion-generated imagescited by 24
- 2025StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Modelscited by 4
- 2025UGD-IML: A Unified Generative Diffusion-based Framework for Constrained and Unconstrained Image Manipulation Localizationcited by 0
- 2026Towards Generalized Image Manipulation Localization via Score-based Modelcited by 0
- 2026Towards Generalized Image Manipulation Localization via Score-based Model16 May 2026
- 2025StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models22 Sep 2025
- 2025UGD-IML: A Unified Generative Diffusion-based Framework for Constrained and Unconstrained Image Manipulation Localization8 Aug 2025
- 2023Weakly-supervised deepfake localization in diffusion-generated images8 Nov 2023
- 2024FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Modelscited by 111
- 2024ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detectioncited by 11
- 2025Unlocking the Forgery Detection Potential of Vanilla MLLMs: A Novel Training-Free Pipelinecited by 0
- 2025Unlocking the Forgery Detection Potential of Vanilla MLLMs: A Novel Training-Free Pipeline17 Nov 2025
- 2024ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detection29 Nov 2024
- 2024FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models3 Oct 2024
- 2023Hierarchical Fine-Grained Image Forgery Detection and Localizationcited by 134
- 2021PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localizationcited by 133
- 2022TruFor: Leveraging all-round clues for trustworthy image forgery detection and localizationcited by 130
- 2021MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detectioncited by 117
- 2023Explicit Visual Prompting for Low-Level Structure Segmentationscited by 113
- 2021Image Manipulation Detection by Multi-View Multi-Scale Supervisioncited by 111
- 2023EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protectioncited by 109
- 2021Learning JPEG Compression Artifacts for Image Manipulation Detection and Localizationcited by 78
- 2022ObjectFormer for Image Manipulation Detection and Localizationcited by 78
- 2021Making Images Real Again: A Comprehensive Survey on Deep Image Compositioncited by 63
- 2023IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformercited by 42
- 2024IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localizationcited by 42
12 most cited of 83 All 83 (JSON)
- 2026GIFTBench: Diagnosing Generalization in Image Forgery Localization and Informing Model Design1 Oct 2026
- 2026GAP-SAM: A Global Artifact Prior for Generalizable AI-Generated Image Manipulation Localization21 Aug 2026
- 2026SARIF: Segment Anything for Robust Image Forensics19 Jun 2026
- 2026Multi-axis Analysis of Image Manipulation Localization19 May 2026
- 2026Off-the-shelf Vision Models Benefit Image Manipulation Localization10 Apr 2026
- 2026DiffFace-Edit: A Diffusion-Based Facial Dataset for Forgery-Semantic Driven Deepfake Detection Analysis20 Jan 2026
- 2025NeXT-IMDL: Build Benchmark for NeXT-Generation Image Manipulation Detection & Localization29 Dec 2025
- 2025Creating Blank Canvas Against AI-enabled Image Forgery27 Nov 2025
- 2025Morphology-optimized Multi-Scale Fusion: Combining Local Artifacts and Mesoscopic Semantics for Deepfake Detection and Localization17 Sep 2025
- 2025Webly-Supervised Image Manipulation Localization via Category-Aware Auto-Annotation28 Aug 2025
- 2025Propose and Rectify: A Forensics-Driven MLLM Framework for Image Manipulation Localization25 Aug 2025
- 2025ForensicsSAM: Toward Robust and Unified Image Forgery Detection and Localization Resisting to Adversarial Attack10 Aug 2025
12 newest of 83 All 83 (JSON)