How do early blind individuals experience auditory motion?

Park, Woon Ju; Fine, Ione

doi:10.1167/jov.22.14.3098

Cited by 9 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, as described in [22], the previous processing is considered as a type of low-pass filter that gradually restores input image's information at lowfrequency signals through the self-attention mechanism at different spatial dimensions. Since it tends to reduce high-frequency signals, a 7×7 convolutional layer is used as a high-pass filter to complement the high-frequency signals.…”

Section: Network Architecturementioning

confidence: 99%

A Unet-like Low-cost Image Inpainting Method Built upon Efficient ViT

Huang,

Feng,

Chen

2024

Preprint

View full text Add to dashboard Cite

Image inpainting is the process of replacing broken or defective regions in an image. Recent models use an ensemble of Transformer and CNN to expand the diversity and accuracy of image inpainting. However, when processing high-resolution images with Transformers, the computational cost can be high due to the need to establish global dependencies. This paper proposes a new inpainting method based on the ViT U-net structure. The network utilises a single memory-bound MHSA and cascade group attention ViT which incorporates an improved adaptive gated convolution in the encoder to extract features and employs a PixelShuffle upsampling in the decoder to generate the restored image. Additionally, it recovers local spatial features at multiple levels to refine details. We evaluate our model on CelebA-HQ, Places2, and Paris StreetView datasets. The experimental results demonstrate that the model achieves faster training speed and less memory consumption with fewer parameters, while matching the current state-of-the-art in terms of quantitatively and qualitatively.

show abstract

Section: Network Architecturementioning

confidence: 99%

A Unet-like Low-cost Image Inpainting Method Built upon Efficient ViT

Huang,

Feng,

Chen

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…We notice that the vertical hybrid layout design leads to unsatisfactory performance in detail recovery. A possible reason is that MSAs at the end of each stage act as spatial smoothing and aggregation [20], thus neglecting details unavoidably. To this end, we propose the I-PLDE module, a parallel branch emphasizing local detail on the top of the vertical hybrid design, inspired by the "divide-and-conquer" idea in [30,32].I-PLDE consists of a 1x1 convolution to match hidden dimension with its parallel branch, three stacked depth-wise convolution layers and an window embedding operation.…”

Section: Dudornext: Towards Hybridizing Cnns and Vitsmentioning

confidence: 99%

“…Finally, DuDoRNet generates (sometimes wrong) details of higher frequency, which are seen especially in soft tissues; while Dual-SwinIR generates a smoother image. In recent works in decomposing Transformer from the basic theory [20] to empirical network design [18,28], a potential direction for modernizing deep learning models arises: hybridizing CNNs and ViTs. While several work [30,32,20] in computer vision show the effectiveness of hybrid structures, there is no research systematically studying a hybrid model for MRI reconstruction.…”

Section: Introductionmentioning

confidence: 99%

DuDoRNeXt: A hybrid model for dual-domain undersampled MRI reconstruction

Gao¹,

Zhou²

2023

Preprint

View full text Add to dashboard Cite

Undersampled MRI reconstruction is crucial for accelerating clinical scanning procedures. Recent deep learning methods for MRI reconstruction adopt CNN or ViT as backbone, which lack in utilizing the complementary properties of CNN and ViT. In this paper, we propose DuDoRNeXt, whose backbone hybridizes CNN and ViT in an domainspecific, intra-stage way. Besides our hybrid vertical layout design, we introduce domain-specific modules for dual-domain reconstruction, namely image-domain parallel local detail enhancement and k-space global initialization. We evaluate different conventions of MRI reconstruction including image-domain, k-space-domain, and dual-domain reconstruction with a reference protocol on the IXI dataset and an in-house multicontrast dataset. DuDoRNeXt achieves significant improvements over competing deep learning methods.

show abstract

“…23 The visual transformer backbone was chosen over a convolutional backbone since convolutional models are considered more vulnerable to high-frequency noise. 24 This is motivated by earlier empirical findings and the concept that convolutional filters are mainly sensitive to textures (high-pass filter), while the multi-head self-attentions in visual transformers capture distant semantic relevances in an image effectively (low-pass filter). We hypothesize that the gap between our real and synthetic data is predominantly found in the textures of objects and less in their shape.…”

Section: Modelmentioning

confidence: 99%

The effect of simulation variety on a deep learning-based military vehicle detector

Eker,

Heslinga,

Ballan

et al. 2023

Artificial Intelligence for Security and Defence Applications

View full text Add to dashboard Cite

Deep learning has emerged as a powerful tool for image analysis in various fields including the military domain. It has the potential to automate and enhance tasks such as object detection, classification, and tracking. Training images for development of such models are typically scarce, due to the restricted nature of this type of data. Consequently, researchers have focused on using synthetic data for model development, since simulated images are fast to generate and can, in theory, make up a large and diverse data set. When using simulated training data it is important to consider the variety needed to bridge the gap between simulated and real data. So far it is not fully understood what variations are important and how much variation is needed. In this study, we investigate the effect of simulation variety. We do so for the development of a deep learning-based military vehicle detector that is evaluated on real-world images of military vehicles. To construct the synthetic training data, 3D models of the vehicles are placed in front of diverse background scenes. We experiment with the number of images, background scene variations, 3D model variations, model textures, camera-object distance, and various object rotations. The insight that we gain can be used to prioritize future efforts towards creating synthetic data for deep learning-based object detection models.

show abstract

How do early blind individuals experience auditory motion?

Cited by 9 publications

References 0 publications

A Unet-like Low-cost Image Inpainting Method Built upon Efficient ViT

A Unet-like Low-cost Image Inpainting Method Built upon Efficient ViT

DuDoRNeXt: A hybrid model for dual-domain undersampled MRI reconstruction

The effect of simulation variety on a deep learning-based military vehicle detector

Contact Info

Product

Resources

About