Orthonormal Product Quantization Network for Scalable Face Image Retrieval
-
Updated
May 12, 2023 - Python
Orthonormal Product Quantization Network for Scalable Face Image Retrieval
basis embedding: a product quantization based model compression method for language models.
Fast Adaptive Similarity Search through Variance‑Aware Quantization
Implementations of different NLP tasks
This repo includes a Sparse Transformer implementation which utilizes PQ to derive the sparsity.
Pytorch implementation of LISA (Linear-Time Self Attention with Codeword Histogram for Efficient Recommendation. WWW 2021)
Transformer-based Embedding Retrieval with Product Quantization for Edge Computing (JavaScript)
Product quantization using nearest neighbor search
Product Quantization Apllication for KNN
Modified inference engine for quantized convolution using product quantization
Simply Product Quantization - Standalone C++ implementation of 3 different product quantization methods
Array quantization and compression
Multiply-ADDitioN-lESS in Go.
Inverted file system for billion-scale ANN search
Converted version of yahoo LOPQ from python2.7 to python3.6
Scene similarity for weak object discovery & classification
Add a description, image, and links to the product-quantization topic page so that developers can more easily learn about it.
To associate your repository with the product-quantization topic, visit your repo's landing page and select "manage topics."