A Multi-Domain Feature Learning Method for Visual Place Recognition

Yin, Peng; Xu, Lingyun; Li, Xue–Qian; Chen, Yin; Li, Yingli; Srivatsan, Rangaprasad Arun; Li, Lü; Ji, Jianmin; He, Yuqing

doi:10.1109/icra.2019.8793752

Cited by 30 publications

(28 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The multi-domain feature learning method [5] proposed by Yin et al is the most similar method to ours. But compared our method of directly learning the features using a neural network, it uses a more complicated technique of first extracting VLAD descriptors and then separating them through neural networks.…”

Section: Feature Learning For Place Recognitionmentioning

confidence: 94%

“…NetVLAD uses a CNN to extract features which are experimentally proven to be robust and independent to changing conditions. Yin et al [5] recently proposed a multi-domain feature learning method, which first extracts VLAD features and then separate condition-invariant features from them using a GAN architecture.…”

Section: Feature Learning For Place Recognitionmentioning

confidence: 99%

“…Consequently, training the model to an ideal level with limited computational resources and time is somewhat challenging. To improve the training efficiency and to make the model more practical for the place recognition and localization task, we propose adding a feature consistency loss (5), built on the encoded features of different domains and shown in Figure 2. The feature consistency loss can be regarded as a kind of regularization term to make the model more robust and easier to train.…”

Section: B Feature Consistency Lossmentioning

confidence: 99%

See 2 more Smart Citations

Retrieval-based Localization Based on Domain-invariant Feature Learning under Changing Environments

Wang

Liu

et al. 2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Visual localization is a crucial problem in mobile robotics and autonomous driving. One solution is to retrieve images with known pose from a database for the localization of query images. However, in environments with drastically varying conditions (e.g. illumination changes, seasons, occlusion, dynamic objects), retrieval-based localization is severely hampered and becomes a challenging problem. In this paper, a novel domain-invariant feature learning method (DIFL) is proposed based on ComboGAN, a multi-domain image translation network architecture. By introducing a feature consistency loss (FCL) between the encoded features of the original image and translated image in another domain, we are able to train the encoders to generate domain-invariant features in a self-supervised manner. To retrieve a target image from the database, the query image is first encoded using the encoder belonging to the query domain to obtain a domain-invariant feature vector. We then preform retrieval by selecting the database image with the most similar domain-invariant feature vector. We validate the proposed approach on the CMU-Seasons dataset, where we outperform state-of-the-art learning-based descriptors in retrieval-based localization for high and medium precision scenarios.

show abstract

Section: Feature Learning For Place Recognitionmentioning

confidence: 94%

Section: Feature Learning For Place Recognitionmentioning

confidence: 99%

Section: B Feature Consistency Lossmentioning

confidence: 99%

See 1 more Smart Citation

Retrieval-based Localization Based on Domain-invariant Feature Learning under Changing Environments

Wang

Liu

et al. 2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

show abstract

“…GANs with cycle consistency are also used in [203] to tackle the cross-domain problem, however there the authors directly utilize the feature extracted by the first fully connected layer in the discriminator as image representation to be used for the similarity search. Rather than aligning the features of different domains, another strategy is to learn multi domain features and then separate condition dependent features from the condition invariant ones using a separation module [204].…”

Section: E Adapting To Different Environmental Conditionsmentioning

confidence: 99%

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

“…Artificial intelligence has made great progress in recent years, with most researches focusing on deep learning methods [3][4][5]. Most of the VPR studies use convolutional features [6][7][8][9][10][11][12][13]. Chen et al design a framework using convolutional features and untrainable pooling layers [8].…”

mentioning

confidence: 99%

GSAP: A Global Structure Attention Pooling Method for Graph-Based Visual Place Recognition

Yang

Liu

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

The Visual Place Recognition problem aims to use an image to recognize the location that has been visited before. In most of the scenes revisited, the appearance and view are drastically different. Most previous works focus on the 2-D image-based deep learning method. However, the convolutional features are not robust enough to the challenging scenes mentioned above. In this paper, in order to take advantage of the information that helps the Visual Place Recognition task in these challenging scenes, we propose a new graph construction approach to extract the useful information from an RGB image and a depth image and fuse them in graph data. Then, we deal with the Visual Place Recognition problem as a graph classification problem. We propose a new Global Pooling method—Global Structure Attention Pooling (GSAP), which improves the classification accuracy by improving the expression ability of the Global Pooling component. The experiments show that our GSAP method improves the accuracy of graph classification by approximately 2–5%, the graph construction method improves the accuracy of graph classification by approximately 4–6%, and that the whole Visual Place Recognition model is robust to appearance change and view change.

show abstract

A Multi-Domain Feature Learning Method for Visual Place Recognition

Cited by 30 publications

References 14 publications

Retrieval-based Localization Based on Domain-invariant Feature Learning under Changing Environments

Retrieval-based Localization Based on Domain-invariant Feature Learning under Changing Environments

A Survey on Deep Visual Place Recognition

GSAP: A Global Structure Attention Pooling Method for Graph-Based Visual Place Recognition

Contact Info

Product

Resources

About