On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

10 results for “Squeeze-and-Excitation”

Tiled Squeeze-and-Excite: Channel Attention With Local Spatial Contextstat.ML

Tiled Squeeze-and-Excite improves channel attention with local spatial context.

problem Improving channel attention mechanisms in neural networks.

method Proposes tiled squeeze-and-excite (TSE) framework for channel attention.

result Local context of 7 rows or columns is sufficient for matching global context performance.

channel attention squeeze-and-excite local context global context AI accelerators

2021-07-05abs ↗pdf ↗

Channel Locality Block: A Variant of Squeeze-and-Excitationcs.LG

A new channel locality block improves CNN performance.

problem Improving the performance of convolutional neural networks.

method Proposed a variant of Squeeze-and-Excitation block using convolutional layers to learn nearby channel correlation.

result Our C-Local block achieved higher accuracy than the standard SE block on the cifar-10 dataset.

Attention mechanism Convolutional Neural Networks Channel Attention Squeeze-and-Excitation CNN Performance

2019-01-06abs ↗pdf ↗

RES-SE-NET: Boosting Performance of Resnets by Enhancing Bridge-connectionscs.LG

Res-SE-Net boosts Resnet performance by enhancing bridge-connections.

problem Reduced accuracy in Resnet due to lack of feature map contribution from bridge-connections.

method Proposed Res-SE-Net architecture with Squeeze-and-Excitation (SE) block to quantify and weight feature map importance.

result Res-SE-Net generalizes better than Resnet and SE-Resnet on CIFAR-10 and CIFAR-100 datasets.

ResNet Bridge-connections Squeeze-and-Excitation Feature importance Deep learning

2019-02-16abs ↗pdf ↗

TuNet: End-to-end Hierarchical Brain Tumor Segmentation using Cascaded Networkseess.IV

TuNet improves glioma segmentation accuracy and efficiency.

problem Accurate and efficient glioma segmentation for early treatment.

method End-to-end cascaded network with hierarchical structure and ResNet-like blocks.

result Improved segmentation accuracy and reduced treatment costs.

brain tumors glioma segmentation cascaded networks ResNet

2019-10-11abs ↗pdf ↗

Recalibrating 3D ConvNets with Project & Exciteeess.IV

3D ConvNets improved with Project & Excite for medical imaging segmentation.

problem Improving segmentation performance in 3D medical imaging.

method Proposed Project & Excite (PE) modules for 3D F-CNNs, extending 2D recalibration methods.

result Project & Excite modules boost segmentation performance up to 0.3 in Dice Score.

3D ConvNets recalibration Project & Excite medical imaging segmentation

2020-02-25abs ↗pdf ↗

Multivariate LSTM-FCNs for Time Series Classificationcs.LG

Over the past decade, multivariate time series classification has received great attention. We propose transforming the existing univariate time series classification models, the Long Short Term Memory Fully Convolutional Network (LSTM-FCN) and Attention LSTM-FCN (ALSTM-FCN), into a multivariate time series classificat…

2018-01-14abs ↗pdf ↗

Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNetscs.LG

Skip connections make adversarial examples more transferable in ResNets.

problem Transferability of adversarial examples in ResNets with skip connections.

method Skip Gradient Method (SGM) to craft more transferable adversarial examples.

result SGM improves transferability of adversarial examples in various DNNs.

Adversarial examples ResNets Skip connections Transferability Security

2020-02-14abs ↗pdf ↗

Expansion-Squeeze-Excitation Fusion Network for Elderly Activity Recognitioncs.CV

ESE-FN improves elderly activity recognition accuracy.

problem Recognizing individual actions and human-object interactions in elderly activities.

method Exploits multi-modal features from RGB videos and skeleton sequences using ESE attentions and a new Multi-modal Loss.

result ESE-FN achieves best accuracy on ETRI-Activity3D dataset.

elderly activity recognition multi-modal fusion attention mechanism skeleton sequences RGB videos

2021-12-21abs ↗pdf ↗

Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimizationcs.LG

Single-Path NAS reduces NAS search cost to 3 hours, achieving state-of-the-art mobile image classification.

problem Efficiently automate ConvNet design under mobile latency constraints.

method Single-Path NAS, using one single-path ConvNet with shared parameters.

result Achieves state-of-the-art top-1 ImageNet accuracy (75.62%) in 8 epochs (24 TPU-hours).

AutoML NAS ConvNet Mobile Efficiency

2019-07-01abs ↗pdf ↗

EXFormer: A Multi-Scale Trend-Aware Transformer with Dynamic Variable Selection for Foreign Exchange Returns Predictionq-fin.CP

EXFormer predicts foreign exchange returns with high accuracy using a multi-scale self-attention mechanism and dynamic variable selection.

problem Accurately forecasting daily exchange rate returns in international finance.

method EXFormer uses a multi-scale trend-aware self-attention mechanism with dynamic variable selection and embedded squeeze-and-excitation blocks.

result EXFormer outperforms other models in forecasting daily exchange rate returns, achieving statistically significant improvements in directional accuracy.

foreign exchange Transformer self-attention dynamic variable selection exchange rate returns

2025-12-14abs ↗pdf ↗