Connecting Images through Time and Sources: Introducing Low-data, Heterogeneous Instance Retrieval

by   Dimitri Gominski, et al.

With impressive results in applications relying on feature learning, deep learning has also blurred the line between algorithm and data. Pick a training dataset, pick a backbone network for feature extraction, and voilà ; this usually works for a variety of use cases. But the underlying hypothesis that there exists a training dataset matching the use case is not always met. Moreover, the demand for interconnections regardless of the variations of the content calls for increasing generalization and robustness in features. An interesting application characterized by these problematics is the connection of historical and cultural databases of images. Through the seemingly simple task of instance retrieval, we propose to show that it is not trivial to pick features responding well to a panel of variations and semantic content. Introducing a new enhanced version of the Alegoria benchmark, we compare descriptors using the detailed annotations. We further give insights about the core problems in instance retrieval, testing four state-of-the-art additional techniques to increase performance.



There are no comments yet.


page 2


Challenging deep image descriptors for retrieval in heterogeneous iconographic collections

This article proposes to study the behavior of recent and efficient stat...

Learning Models over Relational Data: A Brief Tutorial

This tutorial overviews the state of the art in learning models over rel...

Unsupervised Feature Learning for Writer Identification and Writer Retrieval

Deep Convolutional Neural Networks (CNN) have shown great success in sup...

SIFT Meets CNN: A Decade Survey of Instance Retrieval

In the early days, content-based image retrieval (CBIR) was studied with...

Deep Image Retrieval: A Survey

In recent years a vast amount of visual content has been generated and s...

Tiny CNN for feature point description for document analysis: approach and dataset

In this paper, we study the problem of feature points description in the...

An Efficient Metric of Automatic Weight Generation for Properties in Instance Matching Technique

The proliferation of heterogeneous data sources of semantic knowledge ba...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.