TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Methods/Squeeze-and-Excitation Block

Squeeze-and-Excitation Block

Computer VisionIntroduced 2000543 papers
Source Paper

Description

The Squeeze-and-Excitation Block is an architectural unit designed to improve the representational power of a network by enabling it to perform dynamic channel-wise feature recalibration. The process is:

  • The block has a convolutional block as an input.
  • Each channel is "squeezed" into a single numeric value using average pooling.
  • A dense layer followed by a ReLU adds non-linearity and output channel complexity is reduced by a ratio.
  • Another dense layer followed by a sigmoid gives each channel a smooth gating function.
  • Finally, we weight each feature map of the convolutional block based on the side network; the "excitation".

Papers Using This Method

HELENA: High-Efficiency Learning-based channel Estimation using dual Neural Attention2025-06-16Analyzing Breast Cancer Survival Disparities by Race and Demographic Location: A Survival Analysis Approach2025-06-08Deep Learning-Based BMD Estimation from Radiographs with Conformal Uncertainty Quantification2025-05-28Intelligent Incident Hypertension Prediction in Obstructive Sleep Apnea2025-05-27Deep Learning for Breast Cancer Detection: Comparative Analysis of ConvNeXT and EfficientNet2025-05-24SuperPure: Efficient Purification of Localized and Distributed Adversarial Patches via Super-Resolution GAN Models2025-05-22Enhancing Federated Survival Analysis through Peer-Driven Client Reputation in Healthcare2025-05-22Vulnerability of Transfer-Learned Neural Networks to Data Reconstruction Attacks in Small-Data Regime2025-05-20Defect Detection in Photolithographic Patterns Using Deep Learning Models Trained on Synthetic Data2025-05-15Real-World fNIRS-Based Brain-Computer Interfaces: Benchmarking Deep Learning and Classical Models in Interactive Gaming2025-05-15V-EfficientNets: Vector-Valued Efficiently Scaled Convolutional Neural Network Models2025-05-08Comparative Analysis of Lightweight Deep Learning Models for Memory-Constrained Devices2025-05-06AnomalyMatch: Discovering Rare Objects of Interest with Semi-supervised and Active Learning2025-05-06CSASN: A Multitask Attention-Based Framework for Heterogeneous Thyroid Carcinoma Classification in Ultrasound Images2025-05-04Conformal Prediction for Indoor Positioning with Correctness Coverage Guarantees2025-05-03Mjölnir: A Deep Learning Parametrization Framework for Global Lightning Flash Density2025-04-28Time Frequency Analysis of EMG Signal for Gesture Recognition using Fine grained Features2025-04-20Training Frozen Feature Pyramid DINOv2 for Eyelid Measurements with Infinite Encoding and Orthogonal Regularization2025-04-01Efficient Building Roof Type Classification: A Domain-Specific Self-Supervised Approach2025-03-28Deep learning-based identification of precipitation clouds from all-sky camera data for observatory safety2025-03-24