Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

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

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

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

SRM

style-based recalibration module

GeneralIntroduced 200033 papers

Description

SRM combines style transfer with an attention mechanism. Its main contribution is style pooling which utilizes both mean and standard deviation of the input features to improve its capability to capture global information. It also adopts a lightweight channel-wise fully-connected (CFC) layer, in place of the original fully-connected layer, to reduce the computational requirements. Given an input feature map $X \in \mathbb{R}^{C \times H \times W}$ , SRM first collects global information by using style pooling ( $\text{SP}(\cdot)$ ) which combines global average pooling and global standard deviation pooling. Then a channel-wise fully connected ( $\text{CFC}(\cdot)$ ) layer (i.e. fully connected per channel), batch normalization $\text{BN}$ and sigmoid function $\sigma$ are used to provide the attention vector. Finally, as in an SE block, the input features are multiplied by the attention vector. Overall, an SRM can be written as: \begin{align} s = F_\text{srm}(X, \theta) & = \sigma (\text{BN}(\text{CFC}(\text{SP}(X)))) \end{align} \begin{align} Y & = s X \end{align} The SRM block improves both squeeze and excitation modules, yet can be added after each residual unit like an SE block.

Papers Using This Method

Learn to Vaccinate: Combining Structure Learning and Effective Vaccination for Epidemic and Outbreak Control2025-06-18 Speculative Reward Model Boosts Decision Making Ability of LLMs Cost-Effectively2025-05-31 Boosting Virtual Agent Learning and Reasoning: A Step-wise, Multi-dimensional, and Generalist Reward Model with Benchmark2025-03-24 Collaboration of Large Language Models and Small Recommendation Models for Device-Cloud Recommendation2025-01-10 Beyond CVaR: Leveraging Static Spectral Risk Measures for Enhanced Decision-Making in Distributional Reinforcement Learning2025-01-03 A Deep Semantic Segmentation Network with Semantic and Contextual Refinements2024-12-11 Robust Universum Twin Support Vector Machine for Imbalanced Data2024-10-27 Enhancing Robustness and Efficiency of Least Square Twin SVM via Granular Computing2024-10-22 HyperDet: Generalizable Detection of Synthesized Images by Generating and Merging A Mixture of Hyper LoRAs2024-10-08 Granular Ball Twin Support Vector Machine2024-10-07 Solution for Authenticity Identification of Typical Target Remote Sensing Images2024-05-03 Structure-Aware Human Body Reshaping with Adaptive Affinity-Graph Network2024-04-22 Assessing Generalization for Subpopulation Representative Modeling via In-Context Learning2024-02-12 Model Selection for Inverse Reinforcement Learning via Structural Risk Minimization2023-12-27 Structural Risk Minimization for Learning Nonlinear Dynamics2023-09-28 Learning via Wasserstein-Based High Probability Generalisation Bounds2023-06-07 Smooth Robustness Measures for Symbolic Control Via Signal Temporal Logic2023-05-16 Auditory distraction in open-plan office environments: The effect of multi-talker acoustics2023-04-14 MDL-based Compressing Sequential Rules2022-12-20 Joint Secure Communication and Radar Beamforming: A Secrecy-Estimation Rate-Based Design2022-11-23