Netvlad

NetVLAD is a deep learning-based image descriptor framework developed by Relja Arandjelović for place recognition and image retrieval. It extends standard CNNs with a trainable VLAD (Vector of Locally Aggregated Descriptors) layer to create compact, robust global descriptors from image features. This implementation includes training code and pretrained models using the Pittsburgh and Tokyo datasets.

Features

Trainable VLAD layer integrated into CNNs
High-performance place recognition and retrieval
Pretrained models and benchmark support
PyTorch/Torch7-based implementations
Evaluation scripts on standard datasets
Includes feature extraction and descriptor matching

Project Samples

Project Activity

See All Activity >

License

MIT License

Follow Netvlad

Netvlad Web Site

Other Useful Business Software

Veeam Data Platform v13.1 - Get Your Free Trial

Secure by design, portable by default. Recover clean, fast, anywhere. Start a free trial.

Try Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.

Try it Free

Rate This Project

User Reviews

Be the first to post a review of Netvlad!

Additional Project Details

Operating Systems

Linux, Mac, Windows

Programming Language

MATLAB

Related Categories

MATLAB Computer Vision Libraries

Registered

2025-07-24

Similar Business Software

Clarifai

Clarifai is a leading AI platform for modeling image, video, text and audio data at scale. Our platform combines computer vision, natural language processing and audio recognition as building blocks for developing better, faster and stronger AI. We help our customers create innovative solutions...

See Software
Deep Block

Deep Block is the world's fastest AI-powered remote sensing imagery analysis solution. Train your own AI models to detect instantly any objects in large satellite, aerial, and drone images. Deep Block's no-code data labeling interface lets you achieve your MLOps projects in days, with no...

See Software
Ximilar

Ximilar is the first MLaaS platform for training and fine-tuning vision-language models without coding, enabling multimodal AI without in-house research teams. Build and train custom models on your own image and text data, then deploy via a single API click. Chain multiple models into...

See Software
Eyewey

Train your own models, get access to pre-trained computer vision models and app templates, learn how to create AI apps or solve a business problem using computer vision in a couple of hours. Start creating your own dataset for detection by adding the images of the object you need to train. You...

See Software
Visual Layer

Visual Layer is a platform for working with large volumes of image and video data. It supports visual search, filtering, tagging, and dataset structuring across raw files, metadata, and labels. No code is required, and both technical and non-technical teams use it in production. Common...

See Software
Detectnix Vision

Detectnix Vision is an AI-powered adult content, NSFW, and porn scanner for Windows that detects explicit and nude images stored on your computer — entirely offline, with no cloud uploads or third-party processing. Using on-device AI models, it scans JPG, JPEG, PNG, WEBP, and BMP files across...

See Software