Res‐SE‐Net: Boosting Performance of ResNets by Enhancing Bridge Connections

Varshaneya, V; Balasubramanian, Siva; Gera, Darshan

doi:10.1002/9781119769262.ch4

Cited by 6 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare our method with our baselines and counterparts on three datasets, whose results are given in Tables 2 and 3. In addition, compared with other latest results [43]- [46], [48], ResNet-20-RSoRT improves consistently them. Especially, for SE-ResNet-20 [46], the comparison shows the effectiveness of second-order responses captured by RSoRT module.…”

Section: Comparison With Our Baselines and Counterpartsmentioning

confidence: 53%

See 1 more Smart Citation

Second-Order Response Transform Attention Network for Image Classification

et al. 2019

View full text Add to dashboard Cite

Embedding second-order operations into deep convolutional neural networks (CNNs) has recently shown impressive performance for a number of vision tasks. Specifically, the two-branch secondorder response transform (SoRT) network introduces the element-wise product transform into intermediate layers of CNNs, which facilitates the cross-branch response propagation and achieves promising classification accuracy. However, it fails to adaptively rescale responses of feature maps and largely changes the topology of the original backbone networks, leading to the limitation of generalizability. In order to overcome above problems, we propose a novel Second-order Response Transform Attention Network (SoRTA-Net) for classification tasks. The core of SoRTA-Net is the designed refined second-order response transform (RSoRT) module integrating reasonably the attention Squeeze-and-Excitation (SE) block and second-order response transform. Firstly, SoRTA-Net recalibrates adaptively feature responses by the SE block, and then the outputs are sequentially passed through the second-order response transform block, capturing approximately co-occurrence statistics and providing more nonlinearity. Finally, a shortcut branch is naturally combined with the output of the module to boost propagation. The proposed RSoRT module can be flexibly inserted into existing CNNs without any modification of network topology. Our SoRTA-Net extensively evaluated on three datasets (CIFAR-10, CIFAR-100, and SVHN). The experiments have shown that SoRTA-Net is superior to its baseline and achieves competitive performance.INDEX TERMS Second-order response transform, attention mechanism, convolutional neural network, image classification.

show abstract

Section: Comparison With Our Baselines and Counterpartsmentioning

confidence: 53%

“…In addition, compared with other latest results [43]- [46], [48], ResNet-20-RSoRT improves consistently them. Especially, for SE-ResNet-20 [46], the comparison shows the effectiveness of second-order responses captured by RSoRT module.…”

Section: Comparison With Our Baselines and Counterpartsmentioning

confidence: 53%

Second-Order Response Transform Attention Network for Image Classification

et al. 2019

View full text Add to dashboard Cite

show abstract

“…This modulation directs the network towards task-relevant aspects by suppressing feature responses in irrelevant settings [32,33]. Various attention strategies have been proposed to improve neural network performance [44,45]. In this study, we aim to improve precipitation prediction accuracy by incorporating Squeeze-and-Excitation (SE) SE-UNet and SE-UNet3+ are U-Net and UNet3+ models that incorporate attention modulation.…”

Section: U-net-based Modelsmentioning

confidence: 99%

Enhanced Tropical Cyclone Precipitation Prediction in the Northwest Pacific Using Deep Learning Models and Ensemble Techniques

He,

Li,

Zhang

et al. 2024

Water

View full text Add to dashboard Cite

This study focuses on optimizing precipitation forecast induced by tropical cyclones (TCs) in the Northwest Pacific region, with lead times ranging from 6 to 72 h. The research employs deep learning models, such as U-Net, UNet3+, SE-Net, and SE-UNet3+, which utilize precipitation forecast data from the Global Forecast System (GFS) and real-time GFS environmental background data using a U-Net structure. To comprehensively make use of the precipitation forecasts from these models, we additionally use probabilistic matching (PM) and simple averaging (AVR) in rainfall prediction. The precipitation data from the Global Precipitation Measurement (GPM) Mission serves as the rainfall observation. The results demonstrate that the root mean squared errors (RMSEs) of U-Net, UNet3+, SE-UNet, SE-UNet3+, AVR, and PM are lowered by 8.7%, 10.1%, 9.7%, 10.0%, 11.4%, and 11.5%, respectively, when compared with the RMSE of the GFS TC precipitation forecasts, while the mean absolute errors are reduced by 9.6%, 11.3%, 9.0%, 12.0%, 12.8%, and 13.0%, respectively. Furthermore, the neural network model improves the precipitation threat scores (TSs). On average, the TSs of U-Net, UNet3+, SE-UNet, SE-UNet3+, AVR, and PM are raised by 12.8%, 21.3%, 19.3%, 20.7%, 22.5%, and 22.9%, respectively, compared with the GFS model. Notably, AVR and PM outperform all other individual models, with PM’s performance slightly better than AVR’s. The most important feature variables in optimizing TC precipitation forecast in the Northwest Pacific region based on the UNet-based neural network include GFS precipitation forecast data, land and sea masks, latitudinal winds at 500 hPa, and vertical winds at 500 hPa.

show abstract

“…The SE module [31] is a submodule that can easily be embedded in other classical networks (e.g. MobileNetV3 [32] and RES‐SE‐NET [33]). The largest advantage of the SE module is its strong applicability; it does not change the shape of the feature maps and enhances the network performance by generating channel‐wise attention.…”

Section: Network Architecturementioning

confidence: 99%

Prior‐guided multiscale network for single‐image dehazing

Wang

Cui

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

Single-image dehazing is an important problem because it is a key prerequisite for most high-level computer vision tasks. Traditional prior-based methods adopt priors generated from clear images to restrain the atmospheric scattering model and then recover haze-free images. However, these prior-based methods always encounter over-enhancement, such as halos and colour distortion. To solve this problem, many works use a convolutional neural network to retrieve original images. However, without priors as guidance, these learning-based methods dehaze effectively in synthetic datasets but perform poorly in real scenes. Hence, in this paper, we propose a prior-guided multiscale network for singleimage dehazing named PGMNet. Specifically, prior-based methods are adopted to acquire dehazed images of the training dataset in advance and then send these dehazed images to a parameter-shared encoder to form multiscale features. During the decoding process, these multiscale features are adopted to guide the prior-guided multiscale network to recover more image details. Moreover, considering that these prior-based dehazed images usually contain some over-enhanced regions, a spatial attention guided feature aggregation module and squeeze-and-excitation module are adopted to alleviate colour distortion. The proposed PGMNet takes the advantage of prior-based methods in real haze removal and provides superior performance compared with the state-of-the-art methods on both synthetic and real-world datasets.

show abstract

Res‐SE‐Net: Boosting Performance of ResNets by Enhancing Bridge Connections

Cited by 6 publications

References 8 publications

Second-Order Response Transform Attention Network for Image Classification

Second-Order Response Transform Attention Network for Image Classification

Enhanced Tropical Cyclone Precipitation Prediction in the Northwest Pacific Using Deep Learning Models and Ensemble Techniques

Prior‐guided multiscale network for single‐image dehazing

Contact Info

Product

Resources

About