Exploring Visual Embedding Spaces Induced by Vision Transformers for Online Auto Parts Marketplaces
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910819995877376 |
|---|---|
| author | Armijo, Cameron Rivas, Pablo |
| author_facet | Armijo, Cameron Rivas, Pablo |
| contents | This study examines the capabilities of the Vision Transformer (ViT) model in generating visual embeddings for images of auto parts sourced from online marketplaces, such as Craigslist and OfferUp. By focusing exclusively on single-modality data, the analysis evaluates ViT's potential for detecting patterns indicative of illicit activities. The workflow involves extracting high-dimensional embeddings from images, applying dimensionality reduction techniques like Uniform Manifold Approximation and Projection (UMAP) to visualize the embedding space, and using K-Means clustering to categorize similar items. Representative posts nearest to each cluster centroid provide insights into the composition and characteristics of the clusters. While the results highlight the strengths of ViT in isolating visual patterns, challenges such as overlapping clusters and outliers underscore the limitations of single-modal approaches in this domain. This work contributes to understanding the role of Vision Transformers in analyzing online marketplaces and offers a foundation for future advancements in detecting fraudulent or illegal activities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_05756 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploring Visual Embedding Spaces Induced by Vision Transformers for Online Auto Parts Marketplaces Armijo, Cameron Rivas, Pablo Computer Vision and Pattern Recognition Machine Learning I.5.3; I.2.10; I.5.4 This study examines the capabilities of the Vision Transformer (ViT) model in generating visual embeddings for images of auto parts sourced from online marketplaces, such as Craigslist and OfferUp. By focusing exclusively on single-modality data, the analysis evaluates ViT's potential for detecting patterns indicative of illicit activities. The workflow involves extracting high-dimensional embeddings from images, applying dimensionality reduction techniques like Uniform Manifold Approximation and Projection (UMAP) to visualize the embedding space, and using K-Means clustering to categorize similar items. Representative posts nearest to each cluster centroid provide insights into the composition and characteristics of the clusters. While the results highlight the strengths of ViT in isolating visual patterns, challenges such as overlapping clusters and outliers underscore the limitations of single-modal approaches in this domain. This work contributes to understanding the role of Vision Transformers in analyzing online marketplaces and offers a foundation for future advancements in detecting fraudulent or illegal activities. |
| title | Exploring Visual Embedding Spaces Induced by Vision Transformers for Online Auto Parts Marketplaces |
| topic | Computer Vision and Pattern Recognition Machine Learning I.5.3; I.2.10; I.5.4 |
| url | https://arxiv.org/abs/2502.05756 |