visual-search
Visual-Searchcanva-visual-search-embeddings
Visual Search Embedding Benchmark: Extending Canva's DINOv2 Evaluation
Executive Summary
This benchmark extends Canva's January 2025 engineering evaluation
which chose DINOv2 for production image replacement. We test three newer models released since then
against DINOv2 on 500 design-domain images (advertising posters from the CGL-Dataset).
Key Findings
Metric
Winner
Score
vs DINOv2
Recall@1
facebook/dinov2-base
1.0000
—
Recall@5… See the full description on the dataset page: https://huggingface.co/datasets/prometheus04/canva-visual-search-embeddings.Visual_Search
🌟 This repo contains part of the training dataset for model ThinkMorph-7B.
Dataset Description
We create an enriched interleaved dataset centered on four representative tasks requiring varying degrees of visual engagement and cross-modal interactions, including Jigsaw Assembly, Spatial Navigation, Visual Search and Chart Refocus.
Statistics
Dataset Usage
Data Downloading… See the full description on the dataset page: https://huggingface.co/datasets/ThinkMorph/Visual_Search.abo-visual-search-indexvisual-search-dataset
Visual Search Image Dataset
Overview
This dataset contains 10,343 real-world images organized into 139 semantic categories.
Images represent animals, vehicles, people, food, nature scenes, technology, architecture, and everyday environments.
The dataset was created for experiments in semantic image retrieval and multimodal embedding search using models such as CLIP and vector search libraries like FAISS.
Images were automatically collected using the Python icrawler… See the full description on the dataset page: https://huggingface.co/datasets/darshvit20/visual-search-dataset.visual_search_data