# Towards Perceiving Small Visual Details in Zero-shot Visual Question Answering with Multimodal LLMs

arXiv: https://arxiv.org/abs/2310.16033 · HTML: https://mlsanity.com/paper/2310.16033/

## Key facts

- Cited by 15 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 29 of its 38 references that are in the map.
- First posted on arXiv 24 Oct 2023.

## 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, 29 of 29)

- [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)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [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)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge](https://mlsanity.com/paper/2206.01718/) (2022)
- [Multimodal Few-Shot Learning with Frozen Language Models](https://mlsanity.com/paper/2106.13884/) (2021)
- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [Visual Programming: Compositional visual reasoning without training](https://mlsanity.com/paper/2211.11559/) (2022)
- [Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks](https://mlsanity.com/paper/2208.10442/) (2022)
- [Unifying Vision-and-Language Tasks via Text Generation](https://mlsanity.com/paper/2102.02779/) (2021)
- [RSVQA: Visual Question Answering for Remote Sensing Data](https://mlsanity.com/paper/2003.07333/) (2020)
- [From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models](https://mlsanity.com/paper/2212.10846/) (2022)
- [VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations](https://mlsanity.com/paper/2207.00221/) (2022)
- [Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training](https://mlsanity.com/paper/2210.08773/) (2022)
- [SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events](https://mlsanity.com/paper/2103.15538/) (2021)
- [Rosetta: Large scale system for text detection and recognition in images](https://mlsanity.com/paper/1910.05085/) (2019)
- [Surgical-VQA: Visual Question Answering in Surgical Scenes using Transformer](https://mlsanity.com/paper/2206.11053/) (2022)
- [VQA-Aid: Visual Question Answering for Post-Disaster Damage Assessment and Analysis](https://mlsanity.com/paper/2106.10548/) (2021)
- [A Study of Situational Reasoning for Traffic Understanding](https://mlsanity.com/paper/2306.02520/) (2023)

## Built on by (most cited first, 15 of 15)

- [The Curious Case of Nonverbal Abstract Reasoning with Multi-Modal Large Language Models](https://mlsanity.com/paper/2401.12117/) (2024)
- [CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic Framework](https://mlsanity.com/paper/2603.01607/) (2026)
- [Look Again Before You Abstain:Budgeted Conformal Evidence Acquisition for Reliable Vision-Language Model](https://mlsanity.com/paper/2606.16667/) (2026)
- [LookWise: Knowing When and Where to Look for Fine-Grained Visual Reasoning in Multimodal Large Language Models](https://mlsanity.com/paper/2603.00171/) (2026)
- [Look Where It Matters: Adaptive Visual Refinement for Vision-Language-Action Models](https://mlsanity.com/paper/2608.02197/) (2026)
- [PCRI: Measuring Context Robustness in Multimodal Models for Enterprise Applications](https://mlsanity.com/paper/2509.23879/) (2025)
- [Learning to Look Again: Loss-Gap Supervision for Free-form Crop Routing in Vision-Language Models](https://mlsanity.com/paper/2608.21762/) (2026)
- [Scaling 3D Reasoning with LMMs to Large Robot Mission Environments Using Datagraphs](https://mlsanity.com/paper/2407.10743/) (2024)
- [Task-Aware Resolution Optimization for Visual Large Language Models](https://mlsanity.com/paper/2510.09822/) (2025)
- [Self-Improving Small Object Grounding in LVLMs](https://mlsanity.com/paper/2606.01612/) (2026)
- [LOCUS: Local Visual Cue Search for Enhancing Fine-Grained Perception in Multimodal Large Language Models](https://mlsanity.com/paper/2606.16586/) (2026)
- [Seeing What Is Actually There: PriVE-Bench and PriVE-Tools for Counterfactual Evaluation of Agentic Visual Evidence in VLMs](https://mlsanity.com/paper/2607.16311/) (2026)
- [Giraffe: A Mapping Architecture from Hidden Text Representations to Visual Embeddings for Efficient Graphic Design](https://mlsanity.com/paper/2608.23970/) (2026)
- [The Earth in One Gaze: Training-Free Active Focus for UHR Remote Sensing Understanding](https://mlsanity.com/paper/2609.31747/) (2026)
- [On the Limits of Representation-Based Test-Time Adaptation for Multimodal LLMs](https://mlsanity.com/paper/2610.19892/) (2026)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) have recently achieved promising zero-shot accuracy on visual question answering (VQA) -- a fundamental task affecting various downstream applications and domains. Given the great potential for the broad use of these models, it is important to investigate their limitations in dealing with different image and question properties. In this work, we investigate whether MLLMs can perceive small details as well as large details in images. In particular, we show that their zero-shot accuracy in answering visual questions is very sensitive to the size of the visual subject of the question, declining up to 46% with size. Furthermore, we show that this effect is causal by observing that human visual cropping can significantly mitigate their sensitivity to size. Inspired by the usefulness of human cropping, we then propose five automatic visual cropping methods -- leveraging either external localization models or the decision process of the given MLLM itself -- as inference time mechanisms to improve the zero-shot performance of MLLMs. We study their effectiveness on four popular VQA datasets, and a subset of the VQAv2 dataset tailored towards fine visual details. Our findings suggest that MLLMs should be used with caution in detail-sensitive VQA applications, and that visual cropping is a promising direction to improve their zero-shot performance. To facilitate further investigation of MLLMs' behaviors, our code and data are publicly released.