{"total":273,"rows":[{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631,"area":"moe"},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764,"area":null},{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747,"area":"moe"},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424,"area":null},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408,"area":null},{"id":"2107.12213","title":"Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition","created":"2021-07-26","cited_by_count":322,"area":null},{"id":"2308.00951","title":"From Sparse to Soft Mixtures of Experts","created":"2023-08-02","cited_by_count":248,"area":"moe"},{"id":"2108.05895","title":"Mobile-Former: Bridging MobileNet and Transformer","created":"2021-08-12","cited_by_count":235,"area":null},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2103.14635","title":"PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds","created":"2021-03-26","cited_by_count":211,"area":null},{"id":"2204.12463","title":"Focal Sparse Convolutional Networks for 3D Object Detection","created":"2022-04-26","cited_by_count":142,"area":null},{"id":"2205.03436","title":"EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers","created":"2022-05-06","cited_by_count":116,"area":null},{"id":"2103.06255","title":"Involution: Inverting the Inherence of Convolution for Visual Recognition","created":"2021-03-10","cited_by_count":99,"area":null},{"id":"2210.14793","title":"M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design","created":"2022-10-26","cited_by_count":98,"area":"moe"},{"id":"2303.09030","title":"Large Selective Kernel Network for Remote Sensing Object Detection","created":"2023-03-16","cited_by_count":98,"area":null},{"id":"2110.03742","title":"Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference","created":"2021-09-24","cited_by_count":96,"area":"moe"},{"id":"2203.14216","title":"Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution","created":"2022-03-27","cited_by_count":96,"area":null},{"id":"2105.05003","title":"CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution","created":"2021-05-11","cited_by_count":95,"area":null},{"id":"2301.01081","title":"StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles","created":"2023-01-03","cited_by_count":92,"area":null},{"id":"2104.06403","title":"Lite-HRNet: A Lightweight High-Resolution Network","created":"2021-04-13","cited_by_count":91,"area":null},{"id":"2306.03745","title":"Soft Merging of Experts with Adaptive Routing","created":"2023-06-06","cited_by_count":90,"area":"moe"},{"id":"2103.13425","title":"Diverse Branch Block: Building a Convolution as an Inception-like Unit","created":"2021-03-24","cited_by_count":87,"area":null},{"id":"2103.13258","title":"Dynamic Slimmable Network","created":"2021-03-24","cited_by_count":83,"area":null},{"id":"2402.08609","title":"Mixtures of Experts Unlock Parameter Scaling for Deep RL","created":"2024-02-13","cited_by_count":78,"area":"moe"},{"id":"2202.09769","title":"Dynamic Spatial Propagation Network for Depth Completion","created":"2022-02-20","cited_by_count":71,"area":null},{"id":"2407.11633","title":"Scaling Diffusion Transformers to 16 Billion Parameters","created":"2024-07-16","cited_by_count":66,"area":"diffusion"},{"id":"2203.15737","title":"Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Version","created":"2022-03-29","cited_by_count":59,"area":null},{"id":"2303.01610","title":"Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers","created":"2023-03-02","cited_by_count":59,"area":"moe"},{"id":"2206.04674","title":"Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs","created":"2022-06-09","cited_by_count":58,"area":"moe"},{"id":"2204.00102","title":"Dynamic Multimodal Fusion","created":"2022-03-31","cited_by_count":55,"area":null},{"id":"2209.07947","title":"Omni-Dimensional Dynamic Convolution","created":"2022-09-16","cited_by_count":55,"area":null},{"id":"2104.14107","title":"Decoupled Dynamic Filter Networks","created":"2021-04-29","cited_by_count":53,"area":null},{"id":"2107.07797","title":"Conditional Directed Graph Convolution for 3D Human Pose Estimation","created":"2021-07-16","cited_by_count":52,"area":null},{"id":"2304.06793","title":"Speck: A Smart event-based Vision Sensor with a low latency 327K Neuron Convolutional Neuronal Network Processing Pipeline","created":"2023-04-13","cited_by_count":52,"area":null},{"id":"2303.07820","title":"Adaptive Rotated Convolution for Rotated Object Detection","created":"2023-03-14","cited_by_count":51,"area":null},{"id":"2102.05775","title":"AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition","created":"2021-02-10","cited_by_count":48,"area":null},{"id":"2109.07053","title":"Image Synthesis via Semantic Composition","created":"2021-09-15","cited_by_count":45,"area":null},{"id":"2403.11735","title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","created":"2024-03-18","cited_by_count":44,"area":null},{"id":"2403.14418","title":"OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation","created":"2024-03-21","cited_by_count":44,"area":null},{"id":"2304.01230","title":"SEENN: Towards Temporal Spiking Early-Exit Neural Networks","created":"2023-04-02","cited_by_count":41,"area":null},{"id":"2204.09636","title":"Residual Mixture of Experts","created":"2022-04-20","cited_by_count":39,"area":"moe"},{"id":"2207.10430","title":"The Neural Race Reduction: Dynamics of Abstraction in Gated Networks","created":"2022-07-21","cited_by_count":37,"area":null},{"id":"2305.06382","title":"HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks","created":"2023-05-10","cited_by_count":37,"area":null},{"id":"2310.09832","title":"Merging Experts into One: Improving Computational Efficiency of Mixture of Experts","created":"2023-10-15","cited_by_count":37,"area":"moe"},{"id":"2110.06178","title":"TAda! Temporally-Adaptive Convolutions for Video Understanding","created":"2021-10-12","cited_by_count":36,"area":null},{"id":"2303.14676","title":"PDPP: Projected Diffusion for Procedure Planning in Instructional Videos","created":"2023-03-26","cited_by_count":36,"area":null},{"id":"2103.08756","title":"Revisiting Dynamic Convolution via Matrix Decomposition","created":"2021-03-15","cited_by_count":35,"area":null},{"id":"2209.05227","title":"DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization","created":"2022-09-12","cited_by_count":35,"area":null},{"id":"2306.04073","title":"Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks","created":"2023-06-07","cited_by_count":35,"area":"moe"},{"id":"2306.04652","title":"Language Adaptive Weight Generation for Multi-task Visual Grounding","created":"2023-06-06","cited_by_count":35,"area":null},{"id":"2105.14185","title":"FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions","created":"2021-05-29","cited_by_count":34,"area":null},{"id":"2306.03428","title":"GaitGCI: Generative Counterfactual Intervention for Gait Recognition","created":"2023-06-06","cited_by_count":31,"area":null},{"id":"2208.02879","title":"PointConvFormer: Revenge of the Point-based Convolution","created":"2022-08-04","cited_by_count":30,"area":null},{"id":"2103.10583","title":"Dynamic Transfer for Multi-Source Domain Adaptation","created":"2021-03-19","cited_by_count":29,"area":null},{"id":"2402.12550","title":"Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization","created":"2024-02-19","cited_by_count":28,"area":"moe"},{"id":"2308.11793","title":"Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts","created":"2023-08-22","cited_by_count":27,"area":"moe"},{"id":"2108.05894","title":"MicroNet: Improving Image Recognition with Extremely Low FLOPs","created":"2021-08-12","cited_by_count":26,"area":null},{"id":"2402.12656","title":"HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts","created":"2024-02-20","cited_by_count":26,"area":"moe"},{"id":"2403.11808","title":"Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation","created":"2024-03-18","cited_by_count":25,"area":"moe"},{"id":"2502.20087","title":"OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels","created":"2025-02-27","cited_by_count":25,"area":null},{"id":"2205.05920","title":"Group R-CNN for Weakly Semi-supervised Object Detection with Points","created":"2022-05-12","cited_by_count":24,"area":null},{"id":"2308.01265","title":"Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives","created":"2023-07-18","cited_by_count":24,"area":null},{"id":"2211.01146","title":"DynamicISP: Dynamically Controlled Image Signal Processor for Image Recognition","created":"2022-11-02","cited_by_count":23,"area":null},{"id":"2401.15969","title":"Routers in Vision Mixture of Experts: An Empirical Study","created":"2024-01-29","cited_by_count":23,"area":"moe"},{"id":"2102.11456","title":"Representation Disentanglement for Multi-modal brain MR Analysis","created":"2021-02-23","cited_by_count":22,"area":null},{"id":"2212.12130","title":"Learning to Detect and Segment for Open Vocabulary Object Detection","created":"2022-12-23","cited_by_count":22,"area":"mllm"},{"id":"2303.03932","title":"FFT-based Dynamic Token Mixer for Vision","created":"2023-03-07","cited_by_count":22,"area":null},{"id":"2210.15461","title":"LVP-M3: Language-aware Visual Prompt for Multilingual Multimodal Machine Translation","created":"2022-10-19","cited_by_count":21,"area":null},{"id":"2310.19380","title":"TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition","created":"2023-10-30","cited_by_count":21,"area":null},{"id":"2406.18420","title":"Mixture of Experts in a Mixture of RL settings","created":"2024-06-26","cited_by_count":21,"area":"moe"},{"id":"2105.08714","title":"Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks","created":"2021-05-18","cited_by_count":20,"area":null},{"id":"2102.03026","title":"Instance and Panoptic Segmentation Using Conditional Convolutions","created":"2021-02-05","cited_by_count":19,"area":null},{"id":"2407.03197","title":"DyFADet: Dynamic Feature Aggregation for Temporal Action Detection","created":"2024-07-03","cited_by_count":19,"area":null},{"id":"2503.18783","title":"Frequency Dynamic Convolution for Dense Image Prediction","created":"2025-03-24","cited_by_count":19,"area":null},{"id":"2112.08443","title":"Event-Aware Multimodal Mobility Nowcasting","created":"2021-12-14","cited_by_count":18,"area":null},{"id":"2112.12786","title":"ELSA: Enhanced Local Self-Attention for Vision Transformer","created":"2021-12-23","cited_by_count":18,"area":null},{"id":"2211.06894","title":"Learning from partially labeled data for multi-organ and tumor segmentation","created":"2022-11-13","cited_by_count":18,"area":null},{"id":"2407.10142","title":"PARE-Net: Position-Aware Rotation-Equivariant Networks for Robust Point Cloud Registration","created":"2024-07-14","cited_by_count":18,"area":null},{"id":"2108.10520","title":"Improving Object Detection by Label Assignment Distillation","created":"2021-08-24","cited_by_count":17,"area":null},{"id":"2109.09510","title":"Conditionally Parameterized, Discretization-Aware Neural Networks for Mesh-Based Modeling of Physical Systems","created":"2021-09-15","cited_by_count":17,"area":null},{"id":"2107.10771","title":"EAN: Event Adaptive Network for Enhanced Action Recognition","created":"2021-07-22","cited_by_count":16,"area":null},{"id":"2204.01244","title":"Dynamic Focus-aware Positional Queries for Semantic Segmentation","created":"2022-04-04","cited_by_count":16,"area":null},{"id":"2404.01143","title":"Condition-Aware Neural Network for Controlled Image Generation","created":"2024-04-01","cited_by_count":16,"area":null},{"id":"2111.01673","title":"Relational Self-Attention: What's Missing in Attention for Video Understanding","created":"2021-11-02","cited_by_count":15,"area":null},{"id":"2203.03253","title":"Dynamic MLP for Fine-Grained Image Classification by Leveraging Geographical and Temporal Information","created":"2022-03-07","cited_by_count":15,"area":null},{"id":"2306.03445","title":"MetaGait: Learning to Learn an Omni Sample Adaptive Representation for Gait Recognition","created":"2023-06-06","cited_by_count":15,"area":null},{"id":"2503.23135","title":"LSNet: See Large, Focus Small","created":"2025-03-29","cited_by_count":15,"area":null},{"id":"2112.11037","title":"SOIT: Segmenting Objects with Instance-Aware Transformers","created":"2021-12-21","cited_by_count":14,"area":null},{"id":"2203.06852","title":"Continual Learning for Multivariate Time Series Tasks with Variable Input Dimensions","created":"2022-03-14","cited_by_count":14,"area":null},{"id":"2204.10598","title":"Sparsely-gated Mixture-of-Expert Layers for CNN Interpretability","created":"2022-04-22","cited_by_count":14,"area":"moe"},{"id":"2211.13491","title":"Spatial Mixture-of-Experts","created":"2022-11-24","cited_by_count":14,"area":"moe"},{"id":"2304.09801","title":"MetaBEV: Solving Sensor Failures for BEV Detection and Map Segmentation","created":"2023-04-19","cited_by_count":14,"area":null},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2410.01930","title":"Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL","created":"2024-10-02","cited_by_count":14,"area":"deeprl"},{"id":"2105.07085","title":"MutualNet: Adaptive ConvNet via Mutual Learning from Different Model Configurations","created":"2021-05-14","cited_by_count":13,"area":null},{"id":"2107.08982","title":"InsPose: Instance-Aware Networks for Single-Stage Multi-Person Pose Estimation","created":"2021-07-19","cited_by_count":13,"area":null},{"id":"2107.13155","title":"Improving Video Instance Segmentation via Temporal Pyramid Routing","created":"2021-07-28","cited_by_count":13,"area":null},{"id":"2206.04665","title":"AGConv: Adaptive Graph Convolution on 3D Point Clouds","created":"2022-06-09","cited_by_count":13,"area":null},{"id":"2110.11048","title":"K-Lane: Lidar Lane Dataset and Benchmark for Urban Roads and Highways","created":"2021-10-21","cited_by_count":12,"area":null},{"id":"2205.14280","title":"Fast Object Placement Assessment","created":"2022-05-28","cited_by_count":12,"area":null}],"next_cursor":"100"}