Papers with Code 아카이브
Knowledge Distillation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 11
- 보존된 평가 기록
- 90
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/xiaolilaoli/tiny_bert_ms
TinyBERT: Distilling BERT for Natural Language Understanding
https://github.com/xiaomingzhid/sskd
Semi-Supervised Domain Generalizable Person Re-Identification
https://github.com/xiaopp123/bert_explain
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/xingyu-lin/softagent
SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation
https://github.com/xinshaoamoswang/proselflc-at
ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks
https://github.com/xitianxiaofeixue/BERT
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/xqnwang/fuma
GRATIS: GeneRAting TIme Series with diverse and controllable characteristics
https://github.com/xuanlinli17/autoregressive_inference
https://github.com/xuanyuzhou98/SqueezeSeg
https://github.com/xue-pai/FuxiCTR
https://github.com/xujxyang/opentrans
Global Knowledge Calibration for Fast Open-Vocabulary Segmentation
https://github.com/xxlya/COS598D_Assignment1
https://github.com/xy-guo/mmdetection_kitti
https://github.com/xytpai/retinanet
https://github.com/yan-gao-GY/FedScale
FedScale: Benchmarking Model and System Performance of Federated Learning at Scale
https://github.com/yang3121099/LLM-Neo
LLM-Neo: Parameter Efficient Knowledge Distillation for Large Language Models
https://github.com/yangletliu/finlora
FinLoRA: Benchmarking LoRA Methods for Fine-Tuning LLMs on Financial Datasets
https://github.com/yangyanli/PointCNN
https://github.com/yangyucheng000/DiVE
https://github.com/yangyucheng000/Paper-2/tree/main/FedGM-main
FedMD: Heterogenous Federated Learning via Model Distillation
https://github.com/yangyucheng000/Papers/tree/main/DistillExplanation
https://github.com/yangyucheng000/University/tree/main/model-2/fastspeech2_conformer
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/yangze01/Distilling_the_Knowledge_in_a_Neural_Network
https://github.com/yangze01/Distilling_the_Knowledge_in_a_Neural_Network_pytorch
https://github.com/yanmeizhao/MyMmdetection
https://github.com/yaodongyu/projnorm
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
https://github.com/yaq007/cleverhans
Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
https://github.com/yaroslav-moiseev/evidence-based-possibly-best-practices-in-classical-ML
https://github.com/yashkotadia/GatedGCN-PATTERN
https://github.com/yell/kaggle-camera
https://github.com/yhenon/pytorch-retinanet
https://github.com/yifan-fanyi/Pixelhop
PixelHop: A Successive Subspace Learning (SSL) Method for Object Classification
https://github.com/yifan-fanyi/myMCL-Realization
PixelHop: A Successive Subspace Learning (SSL) Method for Object Classification
https://github.com/yijiaceline/Final-Project-Group4
https://github.com/yinanhe/ForgeryNet
ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.