# VIXEN: Visual Text Comparison Network for Image Difference Captioning

arXiv: https://arxiv.org/abs/2402.19119 · HTML: https://mlsanity.com/paper/2402.19119/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 55 references that are in the map.
- First posted on arXiv 29 Feb 2024.

## Builds on (most cited first, 30 of 40)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [Multimodal Few-Shot Learning with Frozen Language Models](https://mlsanity.com/paper/2106.13884/) (2021)
- [SimVLM: Simple Visual Language Model Pretraining with Weak Supervision](https://mlsanity.com/paper/2108.10904/) (2021)
- [LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model](https://mlsanity.com/paper/2304.15010/) (2023)
- [ClipCap: CLIP Prefix for Image Captioning](https://mlsanity.com/paper/2111.09734/) (2021)
- [Self-critical Sequence Training for Image Captioning](https://mlsanity.com/paper/1612.00563/) (2016)
- [Long-term Recurrent Convolutional Networks for Visual Recognition and Description](https://mlsanity.com/paper/1411.4389/) (2014)
- [Meshed-Memory Transformer for Image Captioning](https://mlsanity.com/paper/1912.08226/) (2019)
- [Auto-Encoding Scene Graphs for Image Captioning](https://mlsanity.com/paper/1812.02378/) (2018)
- [Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning](https://mlsanity.com/paper/1612.01887/) (2016)
- [Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts](https://mlsanity.com/paper/2206.02770/) (2022)
- [A Self-Supervised Descriptor for Image Copy Detection](https://mlsanity.com/paper/2202.10261/) (2022)
- [Linearly Mapping from Image to Text Space](https://mlsanity.com/paper/2209.15162/) (2022)
- [From Show to Tell: A Survey on Deep Learning-based Image Captioning](https://mlsanity.com/paper/2107.06912/) (2021)
- [Learning to Describe Differences Between Pairs of Similar Images](https://mlsanity.com/paper/1808.10584/) (2018)
- [Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)](https://mlsanity.com/paper/1412.6632/) (2014)
- [MAGMA -- Multimodal Augmentation of Generative Models through Adapter-based Finetuning](https://mlsanity.com/paper/2112.05253/) (2021)

## Built on by (most cited first, 12 of 12)

- [Img-Diff: Contrastive Data Synthesis for Multimodal Large Language Models](https://mlsanity.com/paper/2408.04594/) (2024)
- [A Survey of Data Synthesis Approaches](https://mlsanity.com/paper/2407.03672/) (2024)
- [Distractors-Immune Representation Learning with Cross-modal Contrastive Regularization for Change Captioning](https://mlsanity.com/paper/2407.11683/) (2024)
- [TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models](https://mlsanity.com/paper/2412.18675/) (2024)
- [Composed Multi-modal Retrieval: A Survey of Approaches and Applications](https://mlsanity.com/paper/2503.01334/) (2025)
- [Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysis](https://mlsanity.com/paper/2408.04909/) (2024)
- [Imagine How To Change: Explicit Procedure Modeling for Change Captioning](https://mlsanity.com/paper/2603.05969/) (2026)
- [DiffSpot: Can VLMs Spot Fine-Grained Visual Differences in Web Interfaces?](https://mlsanity.com/paper/2605.29615/) (2026)
- [C3-Bench: A Context-Aware Change Captioning Benchmark](https://mlsanity.com/paper/2606.25445/) (2026)
- [Beyond Pixel Diffs: Benchmarking Image Change Captioning for Web UI Visual Regression Testing](https://mlsanity.com/paper/2607.01728/) (2026)
- [Different Changes Require Different Reasoning: Change-Type-Specialized Experts for Robust Change Captioning](https://mlsanity.com/paper/2609.01136/) (2026)
- [MinCU: A Fine-Grained Benchmark for Grounded Minimal-Change Understanding in Image Pairs](https://mlsanity.com/paper/2609.23336/) (2026)

## Abstract (arXiv)

We present VIXEN - a technique that succinctly summarizes in text the visual differences between a pair of images in order to highlight any content manipulation present. Our proposed network linearly maps image features in a pairwise manner, constructing a soft prompt for a pretrained large language model. We address the challenge of low volume of training data and lack of manipulation variety in existing image difference captioning (IDC) datasets by training on synthetically manipulated images from the recent InstructPix2Pix dataset generated via prompt-to-prompt editing framework. We augment this dataset with change summaries produced via GPT-3. We show that VIXEN produces state-of-the-art, comprehensible difference captions for diverse image contents and edit types, offering a potential mitigation against misinformation disseminated via manipulated image content. Code and data are available at http://github.com/alexblck/vixen