# Patch Matters: Training-free Fine-grained Image Caption Enhancement via Local Perception

arXiv: https://arxiv.org/abs/2504.06666 · HTML: https://mlsanity.com/paper/2504.06666/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 52 of its 71 references that are in the map.
- First posted on arXiv 9 Apr 2025.

## Builds on (most cited first, 30 of 52)

- [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)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)
- [Object Hallucination in Image Captioning](https://mlsanity.com/paper/1809.02156/) (2018)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)

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

- [Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation](https://mlsanity.com/paper/2605.18740/) (2026)
- [Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception](https://mlsanity.com/paper/2602.11858/) (2026)
- [EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewards](https://mlsanity.com/paper/2511.16672/) (2025)
- [Top-Down Semantic Refinement for Image Captioning](https://mlsanity.com/paper/2510.22391/) (2025)
- [TV2TV: A Unified Framework for Interleaved Language and Video Generation](https://mlsanity.com/paper/2512.05103/) (2025)
- [Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learning](https://mlsanity.com/paper/2603.01696/) (2026)
- [CycleCap: Improving VLMs Captioning Performance via Self-Supervised Cycle Consistency Fine-Tuning](https://mlsanity.com/paper/2603.18282/) (2026)
- [Evaluating Remote Sensing Image Captions Beyond Metric Biases](https://mlsanity.com/paper/2604.22855/) (2026)
- [Gaze into the Details: Locality-Sensitive Enhancement for OCTA Retinal Vessel Segmentation](https://mlsanity.com/paper/2605.20651/) (2026)
- [Towards Open-World Referring Expression Comprehension: A Benchmark with Training-free Multi-task Consistency Checker](https://mlsanity.com/paper/2605.25706/) (2026)
- [A Glance Is All You Need: Single-Pass Fine-Grained Image Captioning with SimLoss](https://mlsanity.com/paper/2609.00591/) (2026)
- [PuzzleMate: Benchmarking MLLMs for Egocentric Puzzle Assistance](https://mlsanity.com/paper/2609.14473/) (2026)

## Abstract (arXiv)

High-quality image captions play a crucial role in improving the performance of cross-modal applications such as text-to-image generation, text-to-video generation, and text-image retrieval. To generate long-form, high-quality captions, many recent studies have employed multimodal large language models (MLLMs). However, current MLLMs often produce captions that lack fine-grained details or suffer from hallucinations, a challenge that persists in both open-source and closed-source models. Inspired by Feature-Integration theory, which suggests that attention must focus on specific regions to integrate visual information effectively, we propose a divide-then-aggregate strategy. Our method first divides the image into semantic and spatial patches to extract fine-grained details, enhancing the model's local perception of the image. These local details are then hierarchically aggregated to generate a comprehensive global description. To address hallucinations and inconsistencies in the generated captions, we apply a semantic-level filtering process during hierarchical aggregation. This training-free pipeline can be applied to both open-source models (LLaVA-1.5, LLaVA-1.6, Mini-Gemini) and closed-source models (Claude-3.5-Sonnet, GPT-4o, GLM-4V-Plus). Extensive experiments demonstrate that our method generates more detailed, reliable captions, advancing multimodal description generation without requiring model retraining. The source code are available at https://github.com/GeWu-Lab/Patch-Matters