Feature Descriptor by Convolution and Pooling Autoencoders

Chen, Lin; Rottensteiner, Franz; Heipke, Christian

doi:10.5194/isprsarchives-xl-3-w2-31-2015

Cited by 10 publications

(12 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It extends our previous descriptor learning work on Convolutional Neural Networks (CNN; Chen et al, 2015). As a CNN has a natural "deep" architecture, we expect this architecture to have a stronger modelling ability which can be used to produce invariance against more challenging transformations, which classical manually designed descriptors cannot cope with.…”

Section: Introductionmentioning

confidence: 74%

Invariant Descriptor Learning Using a Siamese Convolutional Neural Network

Chen¹,

Rottensteiner²,

Heipke³

2016

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

Self Cite

View full text Add to dashboard Cite

ABSTRACT:In this paper we describe learning of a descriptor based on the Siamese Convolutional Neural Network (CNN) architecture and evaluate our results on a standard patch comparison dataset. The descriptor learning architecture is composed of an input module, a Siamese CNN descriptor module and a cost computation module that is based on the L2 Norm. The cost function we use pulls the descriptors of matching patches close to each other in feature space while pushing the descriptors for non-matching pairs away from each other. Compared to related work, we optimize the training parameters by combining a moving average strategy for gradients and Nesterov's Accelerated Gradient. Experiments show that our learned descriptor reaches a good performance and achieves stateof-art results in terms of the false positive rate at a 95% recall rate on standard benchmark datasets.

show abstract

Section: Introductionmentioning

confidence: 74%

Invariant Descriptor Learning Using a Siamese Convolutional Neural Network

Chen¹,

Rottensteiner²,

Heipke³

2016

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Unsupervised learning methods such as autoencoders do not suffer from dependence on labelled data. Chen et al were the first to apply autoencoders to learn local image descriptors [19]. Their method shows promising results, however, the techniques they are using are today no longer modern (e.g.…”

Section: Related Work a Local Image Descriptorsmentioning

confidence: 99%

“…However, they have been less studied so far for learning local image descriptors. The work of Chen et al [19] reported an AEbased descriptors showing promising results, however, the methods they used are no longer considered state of the art. We proposed in our previous work an approach for learning local image descriptors based on convolutional autoencoders [20], [21] and variational autoencoders [22].…”

Section: Introductionmentioning

confidence: 99%

Efficient Local Image Descriptors Learned With Autoencoders

Žižakić

Pižurica

2022

IEEE Access

View full text Add to dashboard Cite

Local image descriptors play a crucial role in many image processing tasks, such as object tracking, object recognition, panorama stitching, and image retrieval. In this paper, we focus on learning local image descriptors in an unsupervised way, using autoencoders and variational autoencoders. We perform a thorough comparative analysis of these two approaches along with an in-depth analysis of the most relevant hyperparameters to guide their optimal selection. In addition to this analysis, we give insights into the difficulties and the importance of selecting right evaluation techniques during the unsupervised learning of the local image descriptors. We explore the extent to which a simple perceptual metric during training can predict the performance on tasks such as patch matching, retrieval and verification. Finally, we propose an improvement to the encoder architecture that yields significant savings in memory complexity, especially in single-image tasks. As a proof of concept, we integrate our descriptor into an inpainting algorithm and illustrate its results when applied to the virtual restoration of master paintings. The source code required to reproduce the presented results has been made available as a repository on GitHub (https://github.com/nimpy/local-img-descr-ae).INDEX TERMS Local image descriptor, autoencoder, variational autoencoder, inpainting, unsupervised deep learning.

show abstract

“…The application of autoencoders to the problem of descriptor learning was first proposed by Chen et al [18]. In our previous work [19], [20], we proposed autoencoder-based patch descriptors designed for applications with many patch comparisons within a single image.…”

Section: Related Workmentioning

confidence: 99%

Learned BRIEF – transferring the knowledge from hand-crafted to learning-based descriptors

Žižakić

Pižurica

2020

2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)

View full text Add to dashboard Cite

In this paper, we present a novel approach for designing local image descriptors that learn from data and from hand-crafted descriptors. In particular, we construct a learning model that first mimics the behaviour of a hand-crafted descriptor and then learns to improve upon it in an unsupervised manner. We demonstrate the use of this knowledge-transfer framework by constructing the learned BRIEF descriptor based on the well-known hand-crafted descriptor BRIEF. We implement our learned BRIEF with a convolutional autoencoder architecture. Evaluation on the HPatches benchmark for local image descriptors shows the effectiveness of the proposed approach in the tasks of patch retrieval, patch verification, and image matching.

show abstract

Feature Descriptor by Convolution and Pooling Autoencoders

Cited by 10 publications

References 18 publications

Invariant Descriptor Learning Using a Siamese Convolutional Neural Network

Invariant Descriptor Learning Using a Siamese Convolutional Neural Network

Efficient Local Image Descriptors Learned With Autoencoders

Learned BRIEF – transferring the knowledge from hand-crafted to learning-based descriptors

Contact Info

Product

Resources

About