{"url":"/method/sac","slug":"sac","name":"SAC","full_name":"Switchable Atrous Convolution","full_name_withheld":false,"description_markdown":"**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.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/2006.02334v2","title":"DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Convolutions","url":"/methods/category/convolutions","pwc_aliases":[]}],"n_papers_tagged":168,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/gradual-transition-from-bellman-optimality","title":"Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning","date":"2025-06-06","arxiv_id":"2506.05968","n_code_links":1,"syntology":{"ran":1,"of":4,"unverified":3,"pointer_only":0}},{"paper":"/paper/the-cell-must-go-on-agar-io-for-continual","title":"The Cell Must Go On: Agar.io for Continual Reinforcement Learning","date":"2025-05-23","arxiv_id":"2505.18347","n_code_links":1,"syntology":null},{"paper":null,"title":"Deep reinforcement learning-based longitudinal control strategy for automated vehicles at signalised intersections","date":"2025-05-13","arxiv_id":"2505.08896","n_code_links":0,"syntology":null},{"paper":null,"title":"Monte Carlo Beam Search for Actor-Critic Reinforcement Learning in Continuous Control","date":"2025-05-13","arxiv_id":"2505.09029","n_code_links":0,"syntology":null},{"paper":null,"title":"The Exploratory Multi-Asset Mean-Variance Portfolio Selection using Reinforcement Learning","date":"2025-05-12","arxiv_id":"2505.07537","n_code_links":0,"syntology":null},{"paper":null,"title":"Moderate Actor-Critic Methods: Controlling Overestimation Bias via Expectile Loss","date":"2025-04-14","arxiv_id":"2504.09929","n_code_links":0,"syntology":null},{"paper":null,"title":"Hemodynamic Markers: CFD-Based Prediction of Cerebral Aneurysm Rupture Risk","date":"2025-04-11","arxiv_id":"2504.10524","n_code_links":0,"syntology":null},{"paper":null,"title":"KEA: Keeping Exploration Alive by Proactively Coordinating Exploration Strategies","date":"2025-03-23","arxiv_id":"2503.18234","n_code_links":0,"syntology":null},{"paper":null,"title":"Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns","date":"2025-03-05","arxiv_id":"2503.03660","n_code_links":0,"syntology":null},{"paper":null,"title":"Ensemble RL through Classifier Models: Enhancing Risk-Return Trade-offs in Trading Strategies","date":"2025-02-23","arxiv_id":"2502.17518","n_code_links":0,"syntology":null},{"paper":null,"title":"Value-Based Deep RL Scales Predictably","date":"2025-02-06","arxiv_id":"2502.04327","n_code_links":0,"syntology":null},{"paper":null,"title":"Decorrelated Soft Actor-Critic for Efficient Deep Reinforcement Learning","date":"2025-01-31","arxiv_id":"2501.19133","n_code_links":0,"syntology":null},{"paper":"/paper/neural-operator-based-reinforcement-learning","title":"Neural Operator based Reinforcement Learning for Control of first-order PDEs with Spatially-Varying State Delay","date":"2025-01-30","arxiv_id":"2501.18201","n_code_links":1,"syntology":null},{"paper":"/paper/foundation-for-unbiased-cross-validation-of","title":"Foundation for unbiased cross-validation of spatio-temporal models for species distribution modeling","date":"2025-01-27","arxiv_id":"2502.03480","n_code_links":1,"syntology":null},{"paper":null,"title":"Fundamental MMSE-Rate Performance Limits of Integrated Sensing and Communication Systems","date":"2025-01-02","arxiv_id":"2501.01053","n_code_links":0,"syntology":null},{"paper":"/paper/sample-correlation-for-fingerprinting-deep","title":"Sample Correlation for Fingerprinting Deep Face Recognition","date":"2024-12-30","arxiv_id":"2412.20768","n_code_links":2,"syntology":null},{"paper":null,"title":"Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone","date":"2024-12-09","arxiv_id":"2412.06685","n_code_links":0,"syntology":null},{"paper":null,"title":"Movable Antenna-Equipped UAV for Data Collection in Backscatter Sensor Networks: A Deep Reinforcement Learning-based Approach","date":"2024-11-21","arxiv_id":"2411.13970","n_code_links":0,"syntology":null},{"paper":null,"title":"Segment Any Class (SAC): Multi-Class Few-Shot Semantic Segmentation via Class Region Proposals","date":"2024-11-21","arxiv_id":"2411.13774","n_code_links":0,"syntology":null},{"paper":null,"title":"Adaptive Soft Actor-Critic Framework for RIS-Assisted and UAV-Aided Communication","date":"2024-11-16","arxiv_id":"2411.10882","n_code_links":0,"syntology":null},{"paper":"/paper/cale-continuous-arcade-learning-environment","title":"CALE: Continuous Arcade Learning Environment","date":"2024-10-31","arxiv_id":"2410.23810","n_code_links":1,"syntology":{"ran":0,"of":1,"unverified":1,"pointer_only":1}},{"paper":null,"title":"Corrected Soft Actor Critic for Continuous Control","date":"2024-10-22","arxiv_id":"2410.16739","n_code_links":0,"syntology":null},{"paper":null,"title":"Reinforcement Learning in Non-Markov Market-Making","date":"2024-10-18","arxiv_id":"2410.14504","n_code_links":0,"syntology":null},{"paper":"/paper/simba-simplicity-bias-for-scaling-up","title":"SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning","date":"2024-10-13","arxiv_id":"2410.09754","n_code_links":4,"syntology":{"ran":3,"of":6,"unverified":3,"pointer_only":0}},{"paper":null,"title":"A Visual-Analytical Approach for Automatic Detection of Cyclonic Events in Satellite Observations","date":"2024-09-25","arxiv_id":"2410.08218","n_code_links":0,"syntology":null},{"paper":"/paper/offline-reinforcement-learning-for-learning","title":"Offline Reinforcement Learning for Learning to Dispatch for Job Shop Scheduling","date":"2024-09-16","arxiv_id":"2409.10589","n_code_links":1,"syntology":null},{"paper":"/paper/soft-actor-critic-with-beta-policy-via","title":"Soft Actor-Critic with Beta Policy via Implicit Reparameterization Gradients","date":"2024-09-08","arxiv_id":"2409.04971","n_code_links":1,"syntology":null},{"paper":null,"title":"Stacked Universal Successor Feature Approximators for Safety in Reinforcement Learning","date":"2024-09-06","arxiv_id":"2409.04641","n_code_links":0,"syntology":null},{"paper":null,"title":"Adaptive BESS and Grid Setpoints Optimization: A Model-Free Framework for Efficient Battery Management under Dynamic Tariff Pricing","date":"2024-08-19","arxiv_id":"2408.09989","n_code_links":0,"syntology":null},{"paper":null,"title":"Enhancing Hardware Fault Tolerance in Machines with Reinforcement Learning Policy Gradient Algorithms","date":"2024-07-21","arxiv_id":"2407.15283","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":86},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":65},{"task":"/task/deep-reinforcement-learning","name":"Deep Reinforcement Learning","papers":59},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":50},{"task":"/task/continuous-control","name":"Continuous Control","papers":29},{"task":"/task/continuous-control","name":"continuous-control","papers":28},{"task":"/task/mujoco","name":"MuJoCo","papers":21},{"task":"/task/q-learning","name":"Q-Learning","papers":12},{"task":"/task/openai-gym","name":"OpenAI Gym","papers":9},{"task":"/task/atari-games","name":"Atari Games","papers":8},{"task":"/task/decision-making","name":"Decision Making","papers":8},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":5},{"task":"/task/isac","name":"ISAC","papers":5},{"task":"/task/imitation-learning","name":"Imitation Learning","papers":5},{"task":"/task/scheduling","name":"Scheduling","papers":5},{"task":"/task/integrated-sensing-and-communication","name":"Integrated sensing and communication","papers":4},{"task":"/task/adversarial-defense","name":"Adversarial Defense","papers":3},{"task":"/task/benchmarking","name":"Benchmarking","papers":3},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":3},{"task":"/task/continual-learning","name":"Continual Learning","papers":3}],"tasks_shown":20,"n_tasks":117,"usage_by_year":[{"year":"2020","papers":17},{"year":"2021","papers":41},{"year":"2022","papers":28},{"year":"2023","papers":25},{"year":"2024","papers":42},{"year":"2025","papers":15}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/sac"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}