# Does CLIP perceive art the same way we do?

arXiv: https://arxiv.org/abs/2505.05229 · HTML: https://mlsanity.com/paper/2505.05229/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 42 references that are in the map.
- First posted on arXiv 8 May 2025.

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [Understanding Deep Image Representations by Inverting Them](https://mlsanity.com/paper/1412.0035/) (2014)
- [More Control for Free! Image Synthesis with Semantic Diffusion Guidance](https://mlsanity.com/paper/2112.05744/) (2021)
- [CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders](https://mlsanity.com/paper/2106.14843/) (2021)
- [CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels](https://mlsanity.com/paper/2211.13977/) (2022)
- [Inverting Visual Representations with Convolutional Networks](https://mlsanity.com/paper/1506.02753/) (2015)
- [Task Residual for Tuning Vision-Language Models](https://mlsanity.com/paper/2211.10277/) (2022)
- [Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement](https://mlsanity.com/paper/2304.01195/) (2023)
- [Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features](https://mlsanity.com/paper/2308.11485/) (2023)
- [ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation](https://mlsanity.com/paper/2401.12665/) (2024)
- [A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance](https://mlsanity.com/paper/2309.12530/) (2023)
- [Contrastive Language-Image Pre-Training with Knowledge Graphs](https://mlsanity.com/paper/2210.08901/) (2022)
- [SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classification](https://mlsanity.com/paper/2211.16191/) (2022)
- [Selective Vision-Language Subspace Projection for Few-shot CLIP](https://mlsanity.com/paper/2407.16977/) (2024)
- [CLIP-MUSED: CLIP-Guided Multi-Subject Visual Neural Information Semantic Decoding](https://mlsanity.com/paper/2402.08994/) (2024)
- [What do we learn from inverting CLIP models?](https://mlsanity.com/paper/2403.02580/) (2024)
- [Toward a Holistic Evaluation of Robustness in CLIP Models](https://mlsanity.com/paper/2410.01534/) (2024)
- [Exploring the Adversarial Robustness of CLIP for AI-generated Image Detection](https://mlsanity.com/paper/2407.19553/) (2024)
- [A Critical Assessment of Modern Generative Models' Ability to Replicate Artistic Styles](https://mlsanity.com/paper/2502.15856/) (2025)
- [Faster Image2Video Generation: A Closer Look at CLIP Image Embedding's Impact on Spatio-Temporal Cross-Attentions](https://mlsanity.com/paper/2407.19205/) (2024)
- [Analyzing CLIP's Performance Limitations in Multi-Object Scenarios: A Controlled High-Resolution Study](https://mlsanity.com/paper/2502.19828/) (2025)

## Built on by (most cited first, 2 of 2)

- [Understanding How MLLMs Describe Artworks Using Token Activation Maps](https://mlsanity.com/paper/2606.27947/) (2026)
- [Style or Signature? Artist-Disjoint Evaluation of Style Classification in Frozen Vision Embeddings](https://mlsanity.com/paper/2608.14435/) (2026)

## Abstract (arXiv)

CLIP has emerged as a powerful multimodal model capable of connecting images and text through joint embeddings, but to what extent does it 'see' the same way humans do - especially when interpreting artworks? In this paper, we investigate CLIP's ability to extract high-level semantic and stylistic information from paintings, including both human-created and AI-generated imagery. We evaluate its perception across multiple dimensions: content, scene understanding, artistic style, historical period, and the presence of visual deformations or artifacts. By designing targeted probing tasks and comparing CLIP's responses to human annotations and expert benchmarks, we explore its alignment with human perceptual and contextual understanding. Our findings reveal both strengths and limitations in CLIP's visual representations, particularly in relation to aesthetic cues and artistic intent. We further discuss the implications of these insights for using CLIP as a guidance mechanism during generative processes, such as style transfer or prompt-based image synthesis. Our work highlights the need for deeper interpretability in multimodal systems, especially when applied to creative domains where nuance and subjectivity play a central role.