Knowledge Distillation

Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning IJCAI 2019 Knowledge Distillation for End-to-End Monaural Multi-Talker ASR System Interspeech 2019 Knowledge Distillation for Throat Microphone Speech Recognition Interspeech 2019 Knowledge Distillation via Instance Relationship Graph CVPR 2019 Knowledge Distillation via Route Constrained Optimization ICCV 2019 Knowledge Distillation with Adversarial Samples Supporting Decision Boundary AAAI 2019 Knowledge Extraction with No Observable Data NeurIPS 2019 Knowledge Flow: Improve Upon Your Teachers ICLR 2019 Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons AAAI 2019 Large Scale Incremental Learning CVPR 2019 Learning by Cheating CoRL 2019 Learning Lightweight Lane Detection CNNs by Self Attention Distillation ICCV 2019 Learning Metrics From Teachers: Compact Networks for Image Embedding CVPR 2019 Learning to Steer by Mimicking Features from Heterogeneous Auxiliary Networks AAAI 2019 Learning Without Memorizing CVPR 2019 Learn Spelling from Teachers: Transferring Knowledge from Language Models to Sequence-to-Sequence Speech Recognition Interspeech 2019 Lifelong GAN: Continual Learning for Conditional Image Generation ICCV 2019 LIT: Learned Intermediate Representation Training for Model Compression ICML 2019 M2H-GAN: A GAN-Based Mapping from Machine to Human Transcripts for Speech Understanding Interspeech 2019 MEAL: Multi-Model Ensemble via Adversarial Learning AAAI 2019 Microsoft Research Asia’s Systems for WMT19 ACL 2019 MMAct: A Large-Scale Dataset for Cross Modal Human Action Understanding ICCV 2019 Natural Language Generation for Effective Knowledge Distillation EMNLP 2019 Network Pruning via Transformable Architecture Search NeurIPS 2019 Network Recasting: A Universal Method for Network Architecture Transformation AAAI 2019