IMAGE SEARCH SYSTEM BASED ON THE CLIP MODEL AND VECTOR DATABASES
DOI:
https://doi.org/10.24867/33BE02ArtukovKeywords:
Image search, vector databases, CLIP modelAbstract
This thesis presents an image search system based on the CLIP model and vector databases, enabling efficient search of visual content using textual or image-based queries.
References
[1]openai.com, „https://openai.com/index/clip/ “
[Na mreži].
[2] pinecone.io, „https://www.pinecone.io/“
[Na mreži].
[3] J. R, „kaggle.com,“ [Na mreži]. Available: https://www.kaggle.com/datasets/hsankesara/flickr-image-dataset/data
[4] Radford, Alec, et al. "Learning transferable visual models from natural language supervision." International conference on machine learning. PMLR, 2021.
[5] Y. A. Malkov and D. A. Yashunin, “Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs,” IEEE transactions on pattern analysis and machine intelligence, vol. 42, no. 4, p. 824–836, 2018.
