knowledge distillation

Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift ICCV 2021 PLOP: Learning Without Forgetting for Continual Semantic Segmentation CVPR 2021 PNPDet: Efficient Few-Shot Detection Without Forgetting via Plug-and-Play Sub-Networks WACV 2021 POS-Constrained Parallel Decoding for Non-autoregressive Generation ACL 2021 Positive-Congruent Training: Towards Regression-Free Model Updates CVPR 2021 Positive-Unlabeled Data Purification in the Wild for Object Detection CVPR 2021 PQK: Model Compression via Pruning, Quantization, and Knowledge Distillation Interspeech 2021 PRAL: A Tailored Pre-Training Model for Task-Oriented Dialog Generation ACL 2021 PREMERE: Meta-Reweighting via Self-Ensembling for Point-of-Interest Recommendation AAAI 2021 PR-Net: Preference Reasoning for Personalized Video Highlight Detection ICCV 2021 Probabilistic Model Distillation for Semantic Correspondence CVPR 2021 Progressive Network Grafting for Few-Shot Knowledge Distillation AAAI 2021 Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation NAACL 2021 PSSM-Distil: Protein Secondary Structure Prediction (PSSP) on Low-Quality PSSM by Knowledge Distillation with Contrastive Learning AAAI 2021 QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning NeurIPS 2021 RankDistil: Knowledge Distillation for Ranking AISTATS 2021 Real-Time Uncertainty Estimation in Computer Vision via Uncertainty-Aware Distribution Distillation WACV 2021 Real-Time Video Inference on Edge Devices via Adaptive Model Streaming ICCV 2021 Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer EMNLP 2021 Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation CVPR 2021 Refining Sample Embeddings with Relation Prototypes to Enhance Continual Relation Extraction ACL 2021 Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates ACL 2021 Reinforced Multi-Teacher Selection for Knowledge Distillation AAAI 2021 Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translation ACL 2021 Rethinking Soft Labels for Knowledge Distillation: A Bias–Variance Tradeoff Perspective ICLR 2021