# VisMin: Visual Minimal-Change Understanding

arXiv: https://arxiv.org/abs/2407.16772 · HTML: https://mlsanity.com/paper/2407.16772/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 40 of its 78 references that are in the map.
- First posted on arXiv 23 Jul 2024.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)
- [FLAVA: A Foundational Language And Vision Alignment Model](https://mlsanity.com/paper/2112.04482/) (2021)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents](https://mlsanity.com/paper/2306.16527/) (2023)
- [Visual Spatial Reasoning](https://mlsanity.com/paper/2205.00363/) (2022)
- [MIMIC-IT: Multi-Modal In-Context Instruction Tuning](https://mlsanity.com/paper/2306.05425/) (2023)
- [What's "up" with vision-language models? Investigating their struggle with spatial reasoning](https://mlsanity.com/paper/2310.19785/) (2023)
- [LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models](https://mlsanity.com/paper/2305.13655/) (2023)
- [SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality](https://mlsanity.com/paper/2306.14610/) (2023)

## Built on by (most cited first, 23 of 23)

- [Assessing and Learning Alignment of Unimodal Vision and Language Models](https://mlsanity.com/paper/2412.04616/) (2024)
- [CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally](https://mlsanity.com/paper/2502.03566/) (2025)
- [CCExpert: Advancing MLLM Capability in Remote Sensing Change Captioning with Difference-Aware Integration and a Foundational Dataset](https://mlsanity.com/paper/2411.11360/) (2024)
- [Progress-Aware Video Frame Captioning](https://mlsanity.com/paper/2412.02071/) (2024)
- [Diffusion Classifiers Understand Compositionality, but Conditions Apply](https://mlsanity.com/paper/2505.17955/) (2025)
- [PairBench: Are Vision-Language Models Reliable at Comparing What They See?](https://mlsanity.com/paper/2502.15210/) (2025)
- [The Promise of RL for Autoregressive Image Editing](https://mlsanity.com/paper/2508.01119/) (2025)
- [A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks](https://mlsanity.com/paper/2506.08227/) (2025)
- [Does Feasibility Matter? Understanding the Impact of Feasibility on Synthetic Training Data](https://mlsanity.com/paper/2505.10551/) (2025)
- [AI Research Agents Narrow Scientific Exploration](https://mlsanity.com/paper/2605.27905/) (2026)
- [ABE-CLIP: Training-Free Attribute Binding Enhancement for Compositional Image-Text Matching](https://mlsanity.com/paper/2512.17178/) (2025)
- [Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization](https://mlsanity.com/paper/2605.28615/) (2026)
- [Understanding Space Is Rocket Science -- Only Top Reasoning Models Can Solve Spatial Understanding Tasks](https://mlsanity.com/paper/2509.02175/) (2025)
- [Self-Supervised Learning from Structural Invariance](https://mlsanity.com/paper/2602.02381/) (2026)
- [Beyond Perception Errors: Semantic Fixation in Large Vision-Language Models](https://mlsanity.com/paper/2604.12119/) (2026)
- [From Where Things Are to What They Are For: Benchmarking Spatial-Functional Intelligence in Multimodal LLMs](https://mlsanity.com/paper/2605.02130/) (2026)
- [DiffSpot: Can VLMs Spot Fine-Grained Visual Differences in Web Interfaces?](https://mlsanity.com/paper/2605.29615/) (2026)
- [FaLCon: Facet-Anchored Retrieval with Late Consensus for Sim2Real Text-Based Person Anomaly Search](https://mlsanity.com/paper/2608.09474/) (2026)
- [Spatial Knowledge Graph-Guided Multimodal Synthesis](https://mlsanity.com/paper/2505.22633/) (2025)
- [Half-Truths Break Similarity-Based Retrieval](https://mlsanity.com/paper/2602.23906/) (2026)
- [Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding](https://mlsanity.com/paper/2604.13313/) (2026)
- [DiCoBench: Benchmarking Multi-Image Fine-Grained Perception via Differential and Commonality Visual Cues](https://mlsanity.com/paper/2606.26602/) (2026)
- [MinCU: A Fine-Grained Benchmark for Grounded Minimal-Change Understanding in Image Pairs](https://mlsanity.com/paper/2609.23336/) (2026)

## Abstract (arXiv)

Fine-grained understanding of objects, attributes, and relationships between objects is crucial for visual-language models (VLMs). Existing benchmarks primarily focus on evaluating VLMs' capability to distinguish between two very similar captions given an image. In this paper, we introduce a new, challenging benchmark termed Visual Minimal-Change Understanding (VisMin), which requires models to predict the correct image-caption match given two images and two captions. The image pair and caption pair contain minimal changes, i.e., only one aspect changes at a time from among the following: object, attribute, count, and spatial relation. These changes test the models' understanding of objects, attributes (such as color, material, shape), counts, and spatial relationships between objects. We built an automatic framework using large language models and diffusion models, followed by a rigorous 4-step verification process by human annotators. Empirical experiments reveal that current VLMs exhibit notable deficiencies in understanding spatial relationships and counting abilities. We also generate a large-scale training dataset to finetune CLIP and Idefics2, showing significant improvements in fine-grained understanding across benchmarks and in CLIP's general image-text alignment. We release all resources, including the benchmark, training data, and finetuned model checkpoints, at https://vismin.net/.