Knowledge Distillation

1343 papers with code • 5 benchmarks • 4 datasets

Knowledge distillation is the process of transferring knowledge from a large model to a smaller one. While large models (such as very deep neural networks or ensembles of many models) have higher knowledge capacity than small models, this capacity might not be fully utilized.

Libraries

Use these libraries to find Knowledge Distillation models and implementations

Most implemented papers

Focal Loss for Dense Object Detection

facebookresearch/detectron ICCV 2017

Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training.

Distilling the Knowledge in a Neural Network

labmlai/annotated_deep_learning_paper_implementations 9 Mar 2015

A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.

Well-Read Students Learn Better: On the Importance of Pre-training Compact Models

google-research/bert ICLR 2020

Recent developments in natural language representations have been accompanied by large and expensive models that leverage vast amounts of general-domain text through self-supervised pre-training.

FastSpeech 2: Fast and High-Quality End-to-End Text to Speech

coqui-ai/TTS ICLR 2021

In this paper, we propose FastSpeech 2, which addresses the issues in FastSpeech and better solves the one-to-many mapping problem in TTS by 1) directly training the model with ground-truth target instead of the simplified output from teacher, and 2) introducing more variation information of speech (e. g., pitch, energy and more accurate duration) as conditional inputs.

DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

huggingface/transformers NeurIPS 2019

As Transfer Learning from large-scale pre-trained models becomes more prevalent in Natural Language Processing (NLP), operating these large models in on-the-edge and/or under constrained computational training or inference budgets remains challenging.

Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks

adityac94/Grad_CAM_plus_plus 30 Oct 2017

Over the last decade, Convolutional Neural Network (CNN) models have been highly successful in solving complex vision problems.

Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation

UKPLab/sentence-transformers EMNLP 2020

The training is based on the idea that a translated sentence should be mapped to the same location in the vector space as the original sentence.

TinyBERT: Distilling BERT for Natural Language Understanding

huawei-noah/Pretrained-Language-Model Findings of the Association for Computational Linguistics 2020

To accelerate inference and reduce model size while maintaining accuracy, we first propose a novel Transformer distillation method that is specially designed for knowledge distillation (KD) of the Transformer-based models.

FedMD: Heterogenous Federated Learning via Model Distillation

KarhouTam/FL-bench 8 Oct 2019

With 10 distinct participants, the final test accuracy of each model on average receives a 20% gain on top of what's possible without collaboration and is only a few percent lower than the performance each model would have obtained if all private datasets were pooled and made directly available for all participants.

Distilling Knowledge via Knowledge Review

Jia-Research-Lab/ReviewKD CVPR 2021

Knowledge distillation transfers knowledge from the teacher network to the student one, with the goal of greatly improving the performance of the student network.