exponential moving average

DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding EMNLP 2023 Exploring The Role of Mean Teachers in Self-supervised Masked Auto-Encoders ICLR 2023 How to Scale Your EMA NeurIPS 2023 Language Model Alignment with Elastic Reset NeurIPS 2023 MAFiD: Moving Average Equipped Fusion-in-Decoder for Question Answering over Tabular and Textual Data EACL 2023 Mitigating Negative Transfer in Multi-Task Learning with Exponential Moving Average Loss Weighting Strategies (Student Abstract) AAAI 2023 Noisy Pair Corrector for Dense Retrieval EMNLP 2023 Switching Temporary Teachers for Semi-Supervised Semantic Segmentation NeurIPS 2023 The Edge of Orthogonality: A Simple View of What Makes BYOL Tick ICML 2023 Divergence-aware Federated Self-Supervised Learning ICLR 2022 Momentum Adversarial Distillation: Handling Large Distribution Shifts in Data-Free Knowledge Distillation NeurIPS 2022 SELC: Self-Ensemble Label Correction Improves Learning with Noisy Labels IJCAI 2022 Semi-Supervised Semantic Segmentation via Gentle Teaching Assistant NeurIPS 2022 ZhichunRoad at SemEval-2022 Task 2: Adversarial Training and Contrastive Learning for Multiword Representations SemEval 2022 Exponential Moving Average Normalization for Self-Supervised and Semi-Supervised Learning CVPR 2021 Seminar Learning for Click-Level Weakly Supervised Semantic Segmentation ICCV 2021 The Role of Momentum Parameters in the Optimal Convergence of Adaptive Polyak's Heavy-ball Methods ICLR 2021 Understanding self-supervised learning dynamics without contrastive pairs ICML 2021 AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients NeurIPS 2020 Curriculum Learning by Dynamic Instance Hardness NeurIPS 2020 Robust Online Model Adaptation by Extended Kalman Filter with Exponential Moving Average and Dynamic Multi-Epoch Strategy L4DC 2020 Two Birds, One Stone: A Simple, Unified Model for Text Generation from Structured and Unstructured Data ACL 2020 Dual Student: Breaking the Limits of the Teacher in Semi-Supervised Learning ICCV 2019 Re2EMA: Regularized and Reinitialized Exponential Moving Average for Target Model Update in Object Tracking AAAI 2019 The Unusual Effectiveness of Averaging in GAN Training ICLR 2019