Methods › Computer Vision › Convolutions › SAC
Switchable Atrous Convolution
SAC
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Switchable Atrous Convolution (SAC) softly switches the convolutional computation between different atrous rates and gathers the results using switch functions. The switch functions are spatially dependent, i.e., each location of the feature map might have different switches to control the outputs of SAC. To use SAC in a detector, we convert all the standard 3x3 convolutional layers in the bottom-up backbone to SAC.
Papers archive 2025-07-28
30 shown of 168, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning 6 Jun 2025 · 1 repository · arXiv:2506.05968Syntology ran 1 of 4 samples · 3 unverified
-
The Cell Must Go On: Agar.io for Continual Reinforcement Learning 23 May 2025 · 1 repository · arXiv:2505.18347
-
Deep reinforcement learning-based longitudinal control strategy for automated vehicles at signalised intersections 13 May 2025 · 0 repositories · arXiv:2505.08896
-
Monte Carlo Beam Search for Actor-Critic Reinforcement Learning in Continuous Control 13 May 2025 · 0 repositories · arXiv:2505.09029
-
The Exploratory Multi-Asset Mean-Variance Portfolio Selection using Reinforcement Learning 12 May 2025 · 0 repositories · arXiv:2505.07537
-
Moderate Actor-Critic Methods: Controlling Overestimation Bias via Expectile Loss 14 Apr 2025 · 0 repositories · arXiv:2504.09929
-
Hemodynamic Markers: CFD-Based Prediction of Cerebral Aneurysm Rupture Risk 11 Apr 2025 · 0 repositories · arXiv:2504.10524
-
KEA: Keeping Exploration Alive by Proactively Coordinating Exploration Strategies 23 Mar 2025 · 0 repositories · arXiv:2503.18234
-
Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns 5 Mar 2025 · 0 repositories · arXiv:2503.03660
-
Ensemble RL through Classifier Models: Enhancing Risk-Return Trade-offs in Trading Strategies 23 Feb 2025 · 0 repositories · arXiv:2502.17518
-
Value-Based Deep RL Scales Predictably 6 Feb 2025 · 0 repositories · arXiv:2502.04327
-
Decorrelated Soft Actor-Critic for Efficient Deep Reinforcement Learning 31 Jan 2025 · 0 repositories · arXiv:2501.19133
-
Neural Operator based Reinforcement Learning for Control of first-order PDEs with Spatially-Varying State Delay 30 Jan 2025 · 1 repository · arXiv:2501.18201
-
Foundation for unbiased cross-validation of spatio-temporal models for species distribution modeling 27 Jan 2025 · 1 repository · arXiv:2502.03480
-
Fundamental MMSE-Rate Performance Limits of Integrated Sensing and Communication Systems 2 Jan 2025 · 0 repositories · arXiv:2501.01053
-
Sample Correlation for Fingerprinting Deep Face Recognition 30 Dec 2024 · 2 repositories · arXiv:2412.20768
-
Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone 9 Dec 2024 · 0 repositories · arXiv:2412.06685
-
Movable Antenna-Equipped UAV for Data Collection in Backscatter Sensor Networks: A Deep Reinforcement Learning-based Approach 21 Nov 2024 · 0 repositories · arXiv:2411.13970
-
Segment Any Class (SAC): Multi-Class Few-Shot Semantic Segmentation via Class Region Proposals 21 Nov 2024 · 0 repositories · arXiv:2411.13774
-
Adaptive Soft Actor-Critic Framework for RIS-Assisted and UAV-Aided Communication 16 Nov 2024 · 0 repositories · arXiv:2411.10882
-
CALE: Continuous Arcade Learning Environment 31 Oct 2024 · 1 repository · arXiv:2410.23810Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
-
Corrected Soft Actor Critic for Continuous Control 22 Oct 2024 · 0 repositories · arXiv:2410.16739
-
Reinforcement Learning in Non-Markov Market-Making 18 Oct 2024 · 0 repositories · arXiv:2410.14504
-
SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning 13 Oct 2024 · 4 repositories · arXiv:2410.09754Syntology ran 3 of 6 samples · 3 unverified
-
A Visual-Analytical Approach for Automatic Detection of Cyclonic Events in Satellite Observations 25 Sep 2024 · 0 repositories · arXiv:2410.08218
-
Offline Reinforcement Learning for Learning to Dispatch for Job Shop Scheduling 16 Sep 2024 · 1 repository · arXiv:2409.10589
-
Soft Actor-Critic with Beta Policy via Implicit Reparameterization Gradients 8 Sep 2024 · 1 repository · arXiv:2409.04971
-
Stacked Universal Successor Feature Approximators for Safety in Reinforcement Learning 6 Sep 2024 · 0 repositories · arXiv:2409.04641
-
Adaptive BESS and Grid Setpoints Optimization: A Model-Free Framework for Efficient Battery Management under Dynamic Tariff Pricing 19 Aug 2024 · 0 repositories · arXiv:2408.09989
-
Enhancing Hardware Fault Tolerance in Machines with Reinforcement Learning Policy Gradient Algorithms 21 Jul 2024 · 0 repositories · arXiv:2407.15283
Tasks archive 2025-07-28
20 shown of 117 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections