# Explaining CLIP's performance disparities on data from blind/low vision users

arXiv: https://arxiv.org/abs/2311.17315 · HTML: https://mlsanity.com/paper/2311.17315/

## Key facts

- Cited by 7 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 50 of its 68 references that are in the map.
- First posted on arXiv 29 Nov 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, 30 of 50)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [DataComp: In search of the next generation of multimodal datasets](https://mlsanity.com/paper/2304.14108/) (2023)
- [ImageNet-21K Pretraining for the Masses](https://mlsanity.com/paper/2104.10972/) (2021)
- [ClipCap: CLIP Prefix for Image Captioning](https://mlsanity.com/paper/2111.09734/) (2021)
- [Image Segmentation Using Text and Image Prompts](https://mlsanity.com/paper/2112.10003/) (2021)
- [CRIS: CLIP-Driven Referring Image Segmentation](https://mlsanity.com/paper/2111.15174/) (2021)
- [Scaling Open-Vocabulary Object Detection](https://mlsanity.com/paper/2306.09683/) (2023)
- [Visual Classification via Description from Large Language Models](https://mlsanity.com/paper/2210.07183/) (2022)

## Built on by (most cited first, 7 of 7)

- [No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance](https://mlsanity.com/paper/2404.04125/) (2024)
- [ProgramAlly: Creating Custom Visual Access Programs via Multi-Modal End-User Programming](https://mlsanity.com/paper/2408.10499/) (2024)
- [Understanding How Blind Users Handle Object Recognition Errors: Strategies and Challenges](https://mlsanity.com/paper/2408.03303/) (2024)
- [Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models](https://mlsanity.com/paper/2510.03721/) (2025)
- [Detecting Content Rating Violations in Android Applications: A Vision-Language Approach](https://mlsanity.com/paper/2502.15739/) (2025)
- [AccessShare: Co-designing Data Access and Sharing with Blind People](https://mlsanity.com/paper/2407.19351/) (2024)
- [Cripping AI: Reimagining AI Through Lived Disability Experiences](https://mlsanity.com/paper/2605.02080/) (2026)

## Abstract (arXiv)

Large multi-modal models (LMMs) hold the potential to usher in a new era of automated visual assistance for people who are blind or low vision (BLV). Yet, these models have not been systematically evaluated on data captured by BLV users. We address this by empirically assessing CLIP, a widely-used LMM likely to underpin many assistive technologies. Testing 25 CLIP variants in a zero-shot classification task, we find that their accuracy is 15 percentage points lower on average for images captured by BLV users than web-crawled images. This disparity stems from CLIP's sensitivities to 1) image content (e.g. not recognizing disability objects as well as other objects); 2) image quality (e.g. not being robust to lighting variation); and 3) text content (e.g. not recognizing objects described by tactile adjectives as well as visual ones). We delve deeper with a textual analysis of three common pre-training datasets: LAION-400M, LAION-2B and DataComp-1B, showing that disability content is rarely mentioned. We then provide three examples that illustrate how the performance disparities extend to three downstream models underpinned by CLIP: OWL-ViT, CLIPSeg and DALL-E2. We find that few-shot learning with as few as 5 images can mitigate CLIP's quality-of-service disparities for BLV users in some scenarios, which we discuss alongside a set of other possible mitigations.