Detect-to-Retrieve: Efficient Regional Aggregation for Image Search

Teichmann, Marvin; Araujo, André; Zhu, Menglong; Sim, Jack

doi:10.48550/arxiv.1812.01584

Cited by 6 publications

(9 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, T i is considered, as in DELF, as a block containing W xH D-dimensional descriptors. The recent work of Teichmann et al [24] builds upon the same idea, they describe selected candidate regions in the query with VLAD, and then propose a regional version of the ASMK [25] (another aggregation method) to aggregate these descriptors into a global descriptor.…”

Section: Local Methodsmentioning

confidence: 99%

Challenging Deep Image Descriptors for Retrieval in Heterogeneous Iconographic Collections

Gominski

Porêba²,

Gouet-Brunet³

et al. 2019

Proceedings of the 1st Workshop on Structuring and Understanding of Multimedia heritAge Contents

View full text Add to dashboard Cite

This article proposes to study the behavior of recent and efficient state-of-the-art deep-learning based image descriptors for contentbased image retrieval, facing a panel of complex variations appearing in heterogeneous image datasets, in particular in cultural collections that may involve multi-source, multi-date and multi-view Permission to make digital contents. For this purpose, we introduce a novel dataset, namely Alegoria dataset, consisting of 12,952 iconographic contents representing landscapes of the French territory, and encapsultating a large range of intra-class variations of appearance which were finely labelled. Six deep features (DELF, NetVLAD, GeM, MAC, RMAC, SPoC) and a hand-crafted local descriptor (ORB) are evaluated against these variations. Their performance are discussed, with the objective of providing the reader with research directions for improving image description techniques dedicated to complex heterogeneous datasets that are now increasingly present in topical applications targeting heritage valorization.

show abstract

Section: Local Methodsmentioning

confidence: 99%

Challenging Deep Image Descriptors for Retrieval in Heterogeneous Iconographic Collections

Gominski

Porêba²,

Gouet-Brunet³

et al. 2019

Proceedings of the 1st Workshop on Structuring and Understanding of Multimedia heritAge Contents

View full text Add to dashboard Cite

show abstract

“…In [31], authors utilized deep correspondence matching based on image patches in aerial images for retrieval task. In [32], authors utilized a novel regional aggregated selective match kernel to combine the information from the regions detected into a holistic description. In [33], authors augmented regional-attention network with Regional-Maximum Activation of Convolutions (R-MAC) to improve the retrieval performance.…”

Section: B Deep Features Based Retrievalmentioning

confidence: 99%

Semantics Preserving Hierarchy based Retrieval of Indian heritage monuments

Gupta

Mukherjee

Lall

et al. 2020

Proceedings of the 2nd Workshop on Structuring and Understanding of Multimedia heritAge Contents

View full text Add to dashboard Cite

Monument classification can be performed on the basis of their appearance and shape from coarse to fine categories. Although there is much semantic information present in the monuments which is reflected in the eras they were built, its type or purpose, the dynasty which established it, etc. Particularly, Indian subcontinent exhibits a huge deal of variation in terms of architectural styles owing to its rich cultural heritage. In this paper, we propose a framework that utilizes hierarchy to preserve semantic information while performing image classification or image retrieval. We encode the learnt deep embeddings to construct a dictionary of images and then utilize a re-ranking framework on the the retrieved results using DeLF features. The semantic information preserved in these embeddings helps to classify unknown monuments at higher level of granularity in hierarchy. We have curated a large, novel Indian heritage monuments dataset comprising of images of historical, cultural and religious importance with subtypes of eras, dynasties and architectural styles. We demonstrate the performance of the proposed framework in image classification and retrieval tasks and compare it with other competing methods on this dataset.

show abstract

“…This allows us to extract local features from input images and then perform geometric verification with RANSAC [5]. As follows from the experiments described in [19], DELF and its extension [24] are the state-of-the-art approaches.…”

Section: Related Workmentioning

confidence: 99%

“…Results on RPar with and without distractors in medium and hard modes are presented in Tables 7 and 8. We also added results of methods from [19] and [24] in best settings to these tables.…”

Section: Revisited Paris Datasetmentioning

confidence: 99%

Large Scale Landmark Recognition via Deep Metric Learning

Boiarov¹,

Tyantov²

2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

This paper presents a novel approach for landmark recognition in images that we've successfully deployed at Mail.ru. This method enables us to recognize famous places, buildings, monuments, and other landmarks in user photos. The main challenge lies in the fact that it's very complicated to give a precise definition of what is and what is not a landmark. Some buildings, statues and natural objects are landmarks; others are not. There's also no database with a fairly large number of landmarks to train a recognition model. A key feature of using landmark recognition in a production environment is that the number of photos containing landmarks is extremely small. This is why the model should have a very low false positive rate as well as high recognition accuracy.We propose a metric learning-based approach that successfully deals with existing challenges and efficiently handles a large number of landmarks. Our method uses a deep neural network and requires a single pass inference that makes it fast to use in production. We also describe an algorithm for cleaning landmarks database which is essential for training a metric learning model. We provide an in-depth description of basic components of our method like neural network architecture, the learning strategy, and the features of our metric learning approach. We show the results of proposed solutions in tests that emulate the distribution of photos with and without landmarks from a user collection. We compare our method with others during these tests. The described system has been deployed as a part of a photo recognition solution at Cloud Mail.ru, which is the photo sharing and storage service at Mail.ru Group.

show abstract

Detect-to-Retrieve: Efficient Regional Aggregation for Image Search

Cited by 6 publications

References 32 publications

Challenging Deep Image Descriptors for Retrieval in Heterogeneous Iconographic Collections

Challenging Deep Image Descriptors for Retrieval in Heterogeneous Iconographic Collections

Semantics Preserving Hierarchy based Retrieval of Indian heritage monuments

Large Scale Landmark Recognition via Deep Metric Learning

Contact Info

Product

Resources

About