Unified embedding generation and search engine. Also available on cloud - cloud.marqo.ai
fastdup is a powerful, free tool designed to rapidly generate valuable insights from image and video datasets. It helps enhance the quality of both images and labels, while significantly reducing data operation costs, all with unmatched scalability.
A toy project for visual search, based on deep learning.
Experience the power of Clarifai’s AI platform with the python SDK. 🌟 Star to support our work!
Minimalistic TensorFlow2+ deep metric/similarity learning library with loss functions, miners, and utils as embedding projector.
A neural network based file sorter. Trains an autoencoder to sort images or audio based on the similarity of their encodings, or uses the OpenAI CLIP model.
✨ PicTrace is an advanced Python-based web application that allows users to find visually similar images from a comprehensive photo archive. Leveraging the power of deep learning and modern image processing techniques, PicTrace delivers fast and accurate search functionality that is ideal for tasks such as cataloging...
[CoRL 2025] Search-TTA: A Multimodal Test-Time Adaptation Framework for Visual Search in the Wild
Visual Search in Natural Scenes benchmark
Visual similarity search engine demo with use of PyTorch Metric Learning and Qdrant
[DEPRECATED] Baseline Project for Semantic Searching
Generate synthetic eye-tracking data using deep learning and ACT-R cognitive model
Simple implementation of search for visually similar images using deep learning and vector search. It's based on pretrained ImageNet weights so it doesnt require any additional training
Easy-to-use API to scrape Google Lens results with proxy support, visual search extraction, and a built-in web UI for testing and debugging.
MobileNetV2-UNet semantic segmentation for Starbucks logo detection - 50ms inference with PyTorch Lightning, binary mask output for mobile deployment
Workshop CDK Template to provision infra for the Deep Visual Search workshop
Visual Search Difficulty Prediction Model (Python implementation)
VistAI is an AI-powered visual search for e-commerce, enabling users to upload photos and find visually similar products. Built with CLIP for image matching, FAISS for efficient similarity search, and DQN for optimized recommendations, it features a Flask-based interface. Developed by Team Recoo at Alpha Network.
Sort the search results of Shotit to increase the correctness of Top1 result by using Keras and Faiss.
Add a description, image, and links to the visual-search topic page so that developers can more easily learn about it.
To associate your repository with the visual-search topic, visit your repo's landing page and select "manage topics."