Content-Based Image Retrieval is a well studied problem in computer vision, with retrieval problems generally divided into two groups: category-level retrieval and instance-level retrieval. Given a query image of the Sydney Harbour bridge, for instance, category-level retrieval aims to find any bridge in a given dataset of images, whilst instance-level retrieval must find the Sydney Harbour bridge to be considered a match.
Deep metric learning aims to learn a function mapping image pixels to embedding feature vectors that model the similarity between images.
Ranked #3 on Image Retrieval on CARS196
Despite significant progress of applying deep learning methods to the field of content-based image retrieval, there has not been a software library that covers these methods in a unified manner.
In the benchmark evaluation, the proposed framework achieves the state-of-the-art performance on the CARS196, CUB200-2011, In-shop Clothes and Stanford Online Products on image retrieval tasks by a large margin compared to competing approaches.
Where previous reviews on content-based image retrieval emphasize on what can be seen in an image to bridge the semantic gap, this survey considers what people tag about an image.
The analysis of natural disasters such as floods in a timely manner often suffers from limited data due to a coarse distribution of sensors or sensor failures.
An adversarial query is an image that has been modified to disrupt content-based image retrieval (CBIR) while appearing nearly untouched to the human eye.
Query images presented to content-based image retrieval systems often have various different interpretations, making it difficult to identify the search objective pursued by the user.
Multiple instance learning (MIL) is a variation of traditional supervised learning problems where data (referred to as bags) are composed of sub-elements (referred to as instances) and only bag labels are available.