Unifying Deep Local and Global Features for Image Search
{Global Features, Local Features}
Paper: https://arxiv.org/pdf/2001.05027v4.pdf
Code: https://github.com/tensorflow/models/ tree/master/research/delf
Embedded Files
0) Motivation, Object and Related works:
Motivation:
Image retrieval is the problem of searching an image database for items that are similar to a query image.
To address this task, two main types of image representations have been studied:
global
local image features.
Objectives: DELG, standing for DEep Local and Global features
Unify global and local features into a single deep model, enabling accurate retrieval with efficient feature extraction.
A model that combines:
Generalized mean pooling for global features.
Attentive selection for local features.
The entire network can be learned end-to-end by carefully balancing the gradient flow between two heads – requiring only image-level labels.
We also introduce an autoencoder-based dimensionality reduction technique for local features, which is integrated into the model, improving training efficiency and matching performance.
Comprehensive experiments show that our model achieves state-of-the-art image retrieval on the Revisited Oxford and Paris datasets, and state-of-the-art single-model instance-level recognition on the Google Landmarks dataset v2.
References:
Unifying Deep Local and Global Features for Image Search [Paper]
Page updated
Google Sites
Report abuse