Self-supervised recurrent depth estimation with attention mechanisms

Makarov, Ilya; Bakhanova, Maria; Nikolenko, Sergey I.; Gerasimova, Olga

doi:10.7717/peerj-cs.865

Cited by 29 publications

(6 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sequence-to-sequence data input is necessary for recurrent neural network (RNN) models [ 109 ]. These models have memory capability, which helps the system learn a group of features in sequence images.…”

Section: Input Data Shapes For Mde Applying Deep Learningmentioning

confidence: 99%

“…Figure 8 represents the basic structure of sequence-to-sequence models, which have a sequence of images as input and a sequence of depth maps as an output. Most RNN methods use long short-term memory (LSTM) to learn the long-term dependencies with a three-gate structure [ 109 ]. However, RNN and CNN networks will be combined to extract spatial–temporal features.…”

Section: Input Data Shapes For Mde Applying Deep Learningmentioning

confidence: 99%

See 1 more Smart Citation

Monocular Depth Estimation Using Deep Learning: A Review

Masoumian

Rashwan

Cristiano

et al. 2022

Sensors

View full text Add to dashboard Cite

In current decades, significant advancements in robotics engineering and autonomous vehicles have improved the requirement for precise depth measurements. Depth estimation (DE) is a traditional task in computer vision that can be appropriately predicted by applying numerous procedures. This task is vital in disparate applications such as augmented reality and target tracking. Conventional monocular DE (MDE) procedures are based on depth cues for depth prediction. Various deep learning techniques have demonstrated their potential applications in managing and supporting the traditional ill-posed problem. The principal purpose of this paper is to represent a state-of-the-art review of the current developments in MDE based on deep learning techniques. For this goal, this paper tries to highlight the critical points of the state-of-the-art works on MDE from disparate aspects. These aspects include input data shapes and training manners such as supervised, semi-supervised, and unsupervised learning approaches in combination with applying different datasets and evaluation indicators. At last, limitations regarding the accuracy of the DL-based MDE models, computational time requirements, real-time inference, transferability, input images shape and domain adaptation, and generalization are discussed to open new directions for future research.

show abstract

Section: Input Data Shapes For Mde Applying Deep Learningmentioning

confidence: 99%

Section: Input Data Shapes For Mde Applying Deep Learningmentioning

confidence: 99%

Monocular Depth Estimation Using Deep Learning: A Review

Masoumian

Rashwan

Cristiano

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…1). Indeed, some problems mentioned above can be overcome using depth sensors [14] or depth estimation in supervised [15], [16] and self-supervised learning settings [17] instead of RGB images. Adding segmentation maps to depth information allows us to capture the main features of objects, such as shape and relative position.…”

Section: Introductionmentioning

confidence: 99%

Inpainting Semantic and Depth Features to Improve Visual Place Recognition in the Wild

Semenkov,

Karpov,

Savchenko

et al. 2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

Visual place recognition is one of the core modern computer vision tasks concerned with identifying location based on the image taken there. Modern state-of-the-art approaches heavily rely on RGB images which are largely affected by changes in the same scene such as varying daytime, illumination, seasonal changes, and presence of dynamic objects (people, vehicles). This results into a large difference between the images in the training dataset and the ones taken by a person in real life at the same place as a part of some application, rendering modern approaches less effective. To deal with this problem, we propose a novel approach that uses only geometrical information (shapes of buildings, terrains, trees, and their relevant positions) obtained from depth and semantic maps inpainted to remove dynamic objects. In this paper, we study two versions of the pipeline: the first one uses direct inpainting, and the second utilizes synthetic data to improve the inpainting process. Our most efficient model achieved 60.6% correct answers with synthetic refinement. With direct inpainting, it kept metrics high at 51.1%. With these compelling results, our approach offers a novel and effective alternative to known algorithms, making it an exciting avenue for future research in visual place recognition.

show abstract

“…Recently, the increase of available computational power and the democratised access to big data allowed the resurgence of deep learning algorithms and their applications LeCun et al [2015], Schmidhuber [2015]. With this paradigm shift, current methods now seek to integrate learnable attention mechanisms on an end-to-end basis Jetley et al [2018], with interesting impacts in diverse applications Makarov et al [2022].…”

Section: Introductionmentioning

confidence: 99%

A survey on attention mechanisms for medical applications: are we moving towards better algorithms?

Gonçalves¹,

Rio-Torto²,

Teixeira³

et al. 2022

Preprint

View full text Add to dashboard Cite

The increasing popularity of attention mechanisms in deep learning algorithms for computer vision and natural language processing made these models attractive to other research domains. In healthcare, there is a strong need for tools that may improve the routines of the clinicians and the patients. Naturally, the use of attention-based algorithms for medical applications occurred smoothly. However, being healthcare a domain that depends on high-stake decisions, the scientific community must ponder if these high-performing algorithms fit the needs of medical applications. With this motto, this paper extensively reviews the use of attention mechanisms in machine learning (including Transformers) for several medical applications. This work distinguishes itself from its predecessors by proposing a critical analysis of the claims and potentialities of attention mechanisms presented in the literature through an experimental case study on medical image classification with three different use cases. These experiments focus on the integrating process of attention mechanisms into established deep learning architectures, the analysis of their predictive power, and a visual assessment of their saliency maps generated by post-hoc explanation methods. This paper concludes with a critical analysis of the claims and potentialities presented in the literature about attention mechanisms and proposes future research lines in medical applications that may benefit from these frameworks.

show abstract

Self-supervised recurrent depth estimation with attention mechanisms

Cited by 29 publications

References 74 publications

Monocular Depth Estimation Using Deep Learning: A Review

Monocular Depth Estimation Using Deep Learning: A Review

Inpainting Semantic and Depth Features to Improve Visual Place Recognition in the Wild

A survey on attention mechanisms for medical applications: are we moving towards better algorithms?

Contact Info

Product

Resources

About