paper-with-me

홈 › Papers

Unsupervised Neural Quantization for Compressed-Domain Similarity Search

2019-08-11 · ICCV 2019 10 · Stanislav Morozov, Artem Babenko

We tackle the problem of unsupervised visual descriptors compression, which is a key ingredient of large-scale image retrieval systems. While the deep learning machinery has benefited literally all computer vision pipelines, the existing state-of-the-art compression methods employ shallow architectures, and we aim to close this gap by our paper. In more detail, we introduce a DNN architecture for the unsupervised compressed-domain retrieval, based on multi-codebook quantization. The proposed architecture is designed to incorporate both fast data encoding and efficient distances computation via lookup tables. We demonstrate the exceptional advantage of our scheme over existing quantization approaches on several datasets of visual descriptors via outperforming the previous state-of-the-art by a large margin.

📄 PDF Abstract BibTeX arXiv:1908.03883

Code (2)

stanis-morozov/unq 공식 구현 pytorch
kevin-rn/Efficient-Fact-checking pytorch

Tasks

Image RetrievalQuantizationRetrieval

Similar Papers 제목 키워드 기반

SUBIC: A supervised, structured binary code for image search

2017-08-09 · ICCV 2017 10 · Himalaya Jain, Joaquin Zepeda, Patrick Pérez, Rémi Gribonval

For large-scale visual search, highly compressed yet meaningful representations of images are essential. Structured vector quantizers based on product quantization and its variants are usually employed to achieve such co…

Deep HashingImage RetrievalQuantizationRetrieval

Similarity search in the blink of an eye with compressed indices

2023-04-07 · Cecilia Aguerrebere, Ishwar Bhati, Mark Hildebrand, Mariano Tepper 외

Nowadays, data is represented by vectors. Retrieving those vectors, among millions and billions, that are similar to a given query is a ubiquitous problem, known as similarity search, of relevance for a wide range of app…

Quantization

Billion-scale similarity search with GPUs

2017-02-28 · Jeff Johnson, Matthijs Douze, Hervé Jégou

Similarity search finds application in specialized database systems handling complex data such as images or videos, which are typically represented by high-dimensional features and require specific indexing structures. T…

GPUImage Similarity SearchQuantization

Position-based Scaled Gradient for Model Quantization and Pruning

2020-05-22 · NeurIPS 2020 12 · Jangho Kim, KiYoon Yoo, Nojun Kwak

We propose the position-based scaled gradient (PSG) that scales the gradient depending on the position of a weight vector to make it more compression-friendly. First, we theoretically show that applying PSG to the standa…

Model CompressionPositionQuantization

Q-matrix Unaware Double JPEG Detection using DCT-Domain Deep BiLSTM Network

2021-04-10 · Vinay Verma, Deepak Singh, Nitin Khanna

The double JPEG compression detection has received much attention in recent years due to its applicability as a forensic tool for the most widely used JPEG file format. Existing state-of-the-art CNN-based methods either …

Quantization