Uncategorized

• Neural Network Ensembles
• Neural Network Ensembles, Cross Validation, and Active Learning
• Combining labeled and unlabeled data with co-training
• Ensemble Methods in Machine Learning
• Model Compression
• Learning with Pseudo-Ensembles
• Cross Modal Distillation for Supervision Transfer
• Distilling Model Knowledge
• Learning Using Privileged Information: Similarity Control and Knowledge Transfer
• Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
• Do deep convolutional nets really need to be deep and convolutional?
• MobileID: Face Model Compression by Distilling Knowledge from Neurons
• Recurrent Neural Network Training with Dark Knowledge Transfer
• Adapting Models to Signal Degradation using Distillation - Chyi Su, Subhransu Maji, 2016
• Data-Free Knowledge Distillation For Deep Neural Networks
• Local Affine Approximators for Improving Knowledge Transfer
• Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model
• Revisiting knowledge transfer for training object class detectors
• A Gift from Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning
• Rocket Launching: A Universal and Efficient Framework for Training Well-performing Light Net
• Data Distillation: Towards Omni-Supervised Learning
• Parallel WaveNet: Fast High-Fidelity Speech Synthesis
• Learning from Noisy Labels with Distillation - Jia Li, ICCV 2017
• Deep Mutual Learning
• Distilling a Neural Network Into a Soft Decision Tree
• Multimodal Recurrent Neural Networks with Information Transfer Layers for Indoor Scene Labeling - Pui Chau, Gang Wang, 2018
• Born Again Neural Networks
• YASENN: Explaining Neural Networks via Partitioning Activation Sequences
• Knowledge Distillation with Adversarial Samples Supporting Decision Boundary
• Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons
• Self-supervised knowledge distillation using singular value decomposition
• Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection
• Learning to Steer by Mimicking Features from Heterogeneous Auxiliary Networks
• A Generalized Meta-loss function for regression and classification using privileged information
• Large scale distributed neural network training through online distillation
• KDGAN: Knowledge Distillation with Generative Adversarial Networks
• Deep Face Recognition Model Compression via Knowledge Transfer and Distillation
• Relational Knowledge Distillation
• Graph-based Knowledge Distillation by Multi-head Attention Network
• Knowledge Adaptation for Efficient Semantic Segmentation
• Structured Knowledge Distillation for Semantic Segmentation
• Fast Human Pose Estimation
• MEAL: Multi-Model Ensemble via Adversarial Learning
• Learning Lightweight Lane Detection CNNs by Self Attention Distillation
• Improved Knowledge Distillation via Teacher Assistant: Bridging the Gap Between Student and Teacher - Iman Mirzadeh, Mehrdad Farajtabar, Ang Li, Hassan Ghasemzadeh, AAAI 2020
• A Comprehensive Overhaul of Feature Distillation
• Contrastive Representation Distillation
• Distillation-Based Training for Multi-Exit Architectures
• Learning Metrics from Teachers: Compact Networks for Image Embedding
• On the Efficacy of Knowledge Distillation
• Revisit Knowledge Distillation: a Teacher-free Framework
• Ensemble Distribution Distillation
• Improving Generalization and Robustness with Noisy Collaboration in Knowledge Distillation
• Self-training with Noisy Student improves ImageNet classification - Thang Luong, Quoc V. Le, CVPR 2020
• Variational Student: Learning Compact and Sparser Networks in Knowledge Distillation Framework
• Preparing Lessons: Improve Knowledge Distillation with Better Supervision
• Positive-Unlabeled Compression on the Cloud
• Variational Information Distillation for Knowledge Transfer
• Knowledge Distillation via Instance Relationship Graph
• Knowledge Distillation via Route Constrained Optimization
• Similarity-Preserving Knowledge Distillation
• Distilling Object Detectors with Fine-grained Feature Imitation
• Knowledge Squeezed Adversarial Network Compression
• Stagewise Knowledge Distillation
• Knowledge Distillation from Internal Representations
• Knowledge Flow: Improve Upon Your Teachers - Jen Liu, Jian Peng, Alexander G. Schwing, 2019
• Graph Representation Learning via Multi-task Knowledge Distillation
• Deep geometric knowledge distillation with graphs
• Correlation Congruence for Knowledge Distillation
• Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation
• BAM! Born-Again Multi-Task Networks for Natural Language Understanding - Thang Luong, Urvashi Khandelwal, Christopher D. Manning, Quoc V. Le, ACL 2019
• Self-Knowledge Distillation in Natural Language Processing
• Rethinking Data Augmentation: Self-Supervision and Self-Distillation
• MSD: Multi-Self-Distillation Learning via Multi-classifiers within Deep Neural Networks
• Efficient Video Classification Using Fewer Frames
• Retaining Privileged Information for Multi-Task Learning - Wei Lehman
• Data-Free Learning of Student Networks
• Positive-Unlabeled Compression on the Cloud
• When Does Label Smoothing Help?
• The State of Knowledge Distillation for Classification
• Distilling Task-Specific Knowledge from BERT into Simple Neural Networks
• Channel Distillation: Channel-Wise Attention for Knowledge Distillation
• Residual Knowledge Distillation
• ResKD: Residual-Guided Knowledge Distillation
• Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion
• MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks
• MGD: Matching Guided Distillation
• Reducing the Teacher-Student Gap via Spherical Knowledge Distillation
• Regularizing Class-wise Predictions via Self-knowledge Distillation
• Training data-efficient image transformers & distillation through attention (DeiT)
• Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks - Jin Yoon, 2020
• Cross-Layer Distillation with Semantic Calibration - Ping Mei, Yuan Zhang, Can Wang, Yan Feng, Chun Chen, AAAI 2021
• Subclass Distillation
• MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis
• Knowledge Distillation: A Survey
• Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation - Chul Moon, CVPR 2021
• Complementary Relation Contrastive Distillation
• Distilling Knowledge via Knowledge Review
• Hierarchical Self-supervised Augmented Knowledge Distillation
• Causal Distillation for Language Models
• How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting
• UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition
• MobileSAMv2: Faster Segment Anything to Everything - Ho Kim, Choong Seon Hong, 2023
• Dark knowledge
• Model Compression
• Heterogeneous Knowledge Transfer in Video Emotion Recognition, Attribution and Summarization - Gang Jiang, Boyang Li, Leonid Sigal, 2015
• Cross Modal Distillation for Supervision Transfer
• Deep Model Compression: Distilling Knowledge from Noisy Teachers
• DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer
• Defensive Collaborative Multi-task Training - Defending against Adversarial Attack towards Deep Neural Networks
• Unifying distillation and privileged information - Paz, Léon Bottou, Bernhard Schölkopf, Vladimir Vapnik, ICLR 2016
• Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
• FitNets: Hints for Thin Deep Nets
• Knowledge Distillation for Small-footprint Highway Networks
• Sequence-Level Knowledge Distillation - papernotes](https://github.com/dennybritz/deeplearning-papernotes/blob/master/notes/seq-knowledge-distillation.md), Yoon Kim, Alexander M. Rush, EMNLP 2016
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Like What You Like: Knowledge Distill via Neuron Selectivity Transfer
• Learning Loss for Knowledge Distillation with Conditional Adversarial Networks - Chang Hsu, Jiawei Huang, 2017
• Knowledge Projection for Deep Neural Networks
• Moonshine: Distilling with Cheap Convolutions
• Efficient Neural Architecture Search via Parameters Sharing
• Deep Co-Training for Semi-Supervised Image Recognition
• Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples
• Distill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillation
• Contrastive Representation Distillation
• Positive-Unlabeled Compression on the Cloud
• Precision Shaking and DORPO: Conceptual Foundations of LLM Knowledge Distillation Methods
• Neural Network Ensembles, Cross Validation, and Active Learning
• Distilling the Knowledge in a Neural Network
• Learning Using Privileged Information: Similarity Control and Knowledge Transfer
• Learning Transferable Architectures for Scalable Image Recognition
• Retaining Privileged Information for Multi-Task Learning - Wei Lehman, KDD 2019
• When Does Label Smoothing Help?
• On Distillation of Guided Diffusion Models
• Progressive Distillation for Fast Sampling of Diffusion Models
• TRACT: Denoising Diffusion Models with Transitive Closure Time-Distillation
• Adversarial Diffusion Distillation