Hybrid Skip: A Biologically Inspired Skip Connection for the UNet Architecture

Zioulis, Nikolaos; Albanis, Georgios; Drakoulis, Petros; Álvarez, Federico; Zarpalas, Dimitrios; Daras, Petros

doi:10.1109/access.2022.3175864

Cited by 10 publications

(4 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The original D-LinkNet adopts skip connections to merge the feature maps of the encoder and decoder, aiming to address the issue of spatial and channel information loss caused by the downsampling process. However, due to the significant semantic gap between the connected convolutional feature maps, the direct addition fusion method is prone to loss of image smoothness and the introduction of pseudoboundaries 30 . Therefore, the proposed AtDy-D-LinkNet introduces the CBAM attention module at the skip connection between the encoder and decoder networks, as illustrated in Fig.…”

Section: Methodsmentioning

confidence: 99%

“…However, due to the significant semantic gap between the connected convolutional feature maps, the direct addition fusion method is prone to loss of image smoothness and the introduction of pseudoboundaries. 30 Therefore, the proposed AtDy-D-LinkNet introduces the CBAM attention module at the skip connection between the encoder and decoder networks, as illustrated in Fig. 4.…”

Section: Cbam Attention Modulementioning

confidence: 99%

See 1 more Smart Citation

Integrating semantic segmentation and edge detection for agricultural greenhouse extraction

He,

Jin,

2024

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

Agricultural greenhouses have a negative impact on the ecological environment while bringing huge economic and social benefits. Therefore, it is of great significance to obtain greenhouse information in a timely and accurate manner. Due to the complex spectral characteristics and dense spatial distribution characteristics of greenhouses, although the extraction of greenhouses based on a single semantic segmentation model can extract the area with high precision, the segmentation process has a serious problem of boundary adhesion between greenhouses, which makes it difficult to accurately obtain the quantity of greenhouses. To address this, our study proposes a method for greenhouse extraction that integrates semantic segmentation and edge constraints, using high-spatial-resolution remote sensing images to accurately extract the area and quantity of greenhouses. This method employs an improved semantic segmentation model (AtDy-D-LinkNet) to extract the greenhouse area, which embeds a convolutional attention module into the D-LinkNet and adopts a dynamic upsampling strategy, achieving precise greenhouse extraction. Experiments demonstrate that the improved model increased the recall, precision, F 1 score, and intersection over union by 1.68%, 2.27%, 1.93%, and 3.54%, respectively, compared to the original model. To address the significant edge adhesion issue in semantic segmentation and accurately extract the quantity of greenhouses, we developed an edge constraint approach. This approach uses an edge detection model to extract greenhouse boundaries, further constrains the greenhouse surfaces, separates adhered greenhouses, and outputs vector patches representing individual greenhouses, thereby achieving precise greenhouse quantity extraction. The experiments show that this method effectively combines the advantages of semantic segmentation and edge detection. It not only ensures the accuracy of greenhouse area extraction but also effectively solves the boundary adhesion issue, significantly improving quantity extraction accuracy, resulting in vector patches that align with the actual area, quantity, and spatial distribution of greenhouses. This can provide a data foundation for greenhouse management and planning in agriculture.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Cbam Attention Modulementioning

confidence: 99%

Integrating semantic segmentation and edge detection for agricultural greenhouse extraction

He,

Jin,

2024

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

show abstract

“…Skip Connections: Skip connections were introduced by UNet [25] to forward high-resolution information from the encoder to the decoder via feature fusion. However, a naive fusion of early encoder and late decoder information is hindered by their semantic gap [35]. MultiResUnet [12] replaces simplistic skip connection with a series of residual blocks to alleviate the semantic gap.…”

Section: Mde As Classification Vs Regression Taskmentioning

confidence: 99%

Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention

Agarwal¹,

Arora²

2022

Preprint

View full text Add to dashboard Cite

Monocular Depth Estimation (MDE) aims to predict pixel-wise depth given a single RGB image. For both, the convolutional as well as the recent attention-based models, encoder-decoder-based architectures have been found to be useful due to the simultaneous requirement of global context and pixel-level resolution. Typically, a skip connection module is used to fuse the encoder and decoder features, which comprises of feature map concatenation followed by a convolution operation. Inspired by the demonstrated benefits of attention in a multitude of computer vision problems, we propose an attention-based fusion of encoder and decoder features. We pose MDE as a pixel query refinement problem, where coarsest-level encoder features are used to initialize pixel-level queries, which are then refined to higher resolutions by the proposed Skip Attention Module (SAM). We formulate the prediction problem as ordinal regression over the bin centers that discretize the continuous depth range and introduce a Bin Center Predictor (BCP) module that predicts bins at the coarsest level using pixel queries. Apart from the benefit of image adaptive depth binning, the proposed design helps learn improved depth embedding in initial pixel queries via direct supervision from the ground truth. Extensive experiments on the two canonical datasets, NYUV2 and KITTI, show that our architecture outperforms the state-of-the-art by 5.3% and 3.9%, respectively, along with an improved generalization performance by 9.4% on the SUNRGBD dataset. Code is available at https://github.com/ ashutosh1807/PixelFormer.git.

show abstract

“…Most networks for depth estimates are based on DenseNet, ResNet, VGG, etc., which are time and computation intensive. Lately, UNet–like architectures have been used for depth estimation [ 33 , 34 ] for faster learning and implementation in less computationally intensive systems. The skip connections here inherently lead to boundary preservation of depth maps.…”

Section: Introductionmentioning

confidence: 99%

Nested DWT–Based CNN Architecture for Monocular Depth Estimation

Paul

Mishra

Marimuthu

2023

Sensors

View full text Add to dashboard Cite

Applications such as medical diagnosis, navigation, robotics, etc., require 3D images. Recently, deep learning networks have been extensively applied to estimate depth. Depth prediction from 2D images poses a problem that is both ill–posed and non–linear. Such networks are computationally and time–wise expensive as they have dense configurations. Further, the network performance depends on the trained model configuration, the loss functions used, and the dataset applied for training. We propose a moderately dense encoder–decoder network based on discrete wavelet decomposition and trainable coefficients (LL, LH, HL, HH). Our Nested Wavelet–Net (NDWTN) preserves the high–frequency information that is otherwise lost during the downsampling process in the encoder. Furthermore, we study the effect of activation functions, batch normalization, convolution layers, skip, etc., in our models. The network is trained with NYU datasets. Our network trains faster with good results.

show abstract

Hybrid Skip: A Biologically Inspired Skip Connection for the UNet Architecture

Cited by 10 publications

References 60 publications

Integrating semantic segmentation and edge detection for agricultural greenhouse extraction

Integrating semantic segmentation and edge detection for agricultural greenhouse extraction

Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention

Nested DWT–Based CNN Architecture for Monocular Depth Estimation

Contact Info

Product

Resources

About