← Application Areas
Machine Learning › Application Areas ›

Knowledge Distillation

2907 directly classified papers

Papers per year

Papers

Few-Shot Class-Incremental Learning via Relation Knowledge Distillation AAAI 2021
Knowledge Distillation Based Training of Universal ASR Source Models for Cross-Lingual Transfer INTERSPEECH 2021
Knowledge Distillation for Streaming Transformer–Transducer INTERSPEECH 2021
PRAL: A Tailored Pre-Training Model for Task-Oriented Dialog Generation ACL 2021
Layer-Wise Searching for 1-Bit Detectors CVPR 2021
Retrieval Augmentation Reduces Hallucination in Conversation EMNLP 2021
Investigation of Practical Aspects of Single Channel Speech Separation for ASR INTERSPEECH 2021
Cross-Modal Knowledge Distillation Method for Automatic Cued Speech Recognition INTERSPEECH 2021
Knowledge Distillation for Singing Voice Detection INTERSPEECH 2021
Designing a Hybrid AI Residency AAAI 2021
Ultra Fast Speech Separation Model with Teacher Student Learning INTERSPEECH 2021
Multi-Domain Knowledge Distillation via Uncertainty-Matching for End-to-End ASR Models INTERSPEECH 2021
Teacher Guided Neural Architecture Search for Face Recognition AAAI 2021
Knowledge Refinery: Learning from Decoupled Label AAAI 2021
Split-and-Bridge: Adaptable Class Incremental Learning within a Single Neural Network AAAI 2021
Peer Collaborative Learning for Online Knowledge Distillation AAAI 2021
Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation IJCAI 2021
Isotonic Data Augmentation for Knowledge Distillation IJCAI 2021
MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation IJCNLP 2021
KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation IJCAI 2021
AlphaNet: Improved Training of Supernets with Alpha-Divergence ICML 2021
Show, Attend and Distill: Knowledge Distillation via Attention-based Feature Matching AAAI 2021
Graph-Free Knowledge Distillation for Graph Neural Networks IJCAI 2021
On Self-Distilling Graph Neural Network IJCAI 2021
Federated Model Distillation with Noise-Free Differential Privacy IJCAI 2021