Multi-Scale Context Attention Network for Image Retrieval

Lou, Yihang; Wang, Shiqi; Duan, Ling-Yu

doi:10.1145/3240508.3240602

Cited by 10 publications

(10 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Image retrieval is akin to a "learning-to-rank" problem, therefore it naturally lends itself to metric learning, i.e., learning image descriptors that represent well the similarity under a distance function. Indeed, most studies in VPR train the CNN that generates the image representations with one of two ranking losses: the contrastive loss, using a siamese network setup, [68], [77], [83], or the triplet loss, using a triplet network setup [69], [74], [80], [90]- [92]. Albeit different, these two losses are based on a similar idea.…”

Section: B Learning To Rankmentioning

confidence: 99%

“…One of the most successful and widely used techniques to improve the retrieval result is query expansion (QE) [12], [23], [37], [65], [66], [70], [73], [74], [76], [77], [80], [82], [88], [92], [96], [123], [126], [127], [129], [130], [138]. The idea of query expansion is to use the shortlisted images as a feedback to produce an enriched representation that is re-submitted for a new search through the database.…”

Section: Query Expansionmentioning

confidence: 99%

“…6). Selection of salient regions can be guided by context at multiple scales as demonstrated by MSCAN [92] with a two layer LSTM network. The first layer of the LSTM network generates an initial multi-scale context memory that is then fed to the second LSTM layer to produce a multi-scale aware attention.…”

Section: ) Attention Modules and Weighting Masksmentioning

confidence: 99%

See 2 more Smart Citations

A Survey on Deep Visual Place Recognition

2021

View full text Add to dashboard Cite

In recent years visual place recognition (VPR), i.e., the problem of recognizing the location of images, has received considerable attention from multiple research communities, spanning from computer vision to robotics and even machine learning. This interest is fueled on one hand by the relevance that visual place recognition holds for many applications and on the other hand by the unsolved challenge of making these methods perform reliably in different conditions and environments. This paper presents a survey of the state-of-the-art of research on visual place recognition, focusing on how it has been shaped by the recent advances in deep learning. We start discussing the image representations used in this task and how they have evolved from using hand-crafted to deep-learned features. We further review how metric learning techniques are used to get more discriminative representations, as well as techniques for dealing with occlusions, distractors, and shifts in the visual domain of the images. The survey also provides an overview of the specific solutions that have been proposed for applications in robotics and with aerial imagery. Finally the survey provides a summary of datasets that are used in visual place recognition, highlighting their different characteristics. INDEX TERMS Visual place recognition, image representation learning, deep learning.

show abstract

Section: B Learning To Rankmentioning

confidence: 99%

Section: Query Expansionmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Deep Visual Place Recognition

2021

View full text Add to dashboard Cite

show abstract

“…Visual Place Recognition. Most VPR approaches cast the problem as an image retrieval task [2,14,20,22,24,26,36]. This is mostly due to the fact that recent years have seen a huge increase in large scale datasets that cover entire cities or countries, both for research [6,23,37] and for commercial use (such as Google Street View, Bing Streetside and Apple Maps).…”

Section: Related Workmentioning

confidence: 99%

“…Most of the recent studies have tried to improve upon this task by using deep convolutional neural networks to extract better representa-* The authors equally contributed tions for the retrieval. However, they typically consider the case of queries and gallery images belonging to the same domain [20,22,26,43]. When the query and gallery images belong to different domains, e.g.…”

Section: Introductionmentioning

confidence: 99%

Adaptive-Attentive Geolocalization from few queries: a hybrid approach

Gabriele

Paolicelli

Masone

et al. 2021

2021 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

We address the task of cross-domain visual place recognition, where the goal is to geolocalize a given query image against a labeled gallery, in the case where the query and the gallery belong to different visual domains. To achieve this, we focus on building a domain robust deep network by leveraging over an attention mechanism combined with fewshot unsupervised domain adaptation techniques, where we use a small number of unlabeled target domain images to learn about the target distribution. With our method, we are able to outperform the current state of the art while using two orders of magnitude less target domain images. Finally we propose a new large-scale dataset for cross-domain visual place recognition, called SVOX. Upon acceptance of the paper, code and dataset will be released.

show abstract