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/vuongtrannguyenkhoi/darknet
https://github.com/vztu/BVQA_Benchmark
UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content
https://github.com/vztu/VIDEVAL
UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content
https://github.com/vztu/VIDEVAL_release
UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content
https://github.com/w-sugar/mmdetection
https://github.com/wMito/HuSc3D
HuSc3D: Human Sculpture dataset for 3D object reconstruction
https://github.com/wangjw6/llmob
https://github.com/wangkai930418/attndistill
Attention Distillation: self-supervised vision transformer students need more guidance
https://github.com/wangxianhao/Improved-YOLOv3-for-UAV
https://github.com/wannaa/c-flat
Maintaining Discrimination and Fairness in Class Incremental Learning
https://github.com/wannabeOG/ExpertNet-Pytorch
https://github.com/wasserth/totalsegmentator
https://github.com/wataru-nakata/fastspeech2-jsut
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/wendelinboehmer/dcg
https://github.com/wenet-e2e/wetts
Unified Mandarin TTS Front-end Based on Distilled BERT Model
https://github.com/wenhuchen/data-to-text-evaluation-metric
https://github.com/wenlai-lavine/jola
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
https://github.com/wenyueh/llm-recsys-id
https://github.com/westny/neural-stability
Which priors matter? Benchmarking models for learning latent dynamics
https://github.com/williamccondori/YOLO-NFPA
https://github.com/witwickey/darknet
https://github.com/wmdataphys/FM4DIRC
Generative Models for Fast Simulation of Cherenkov Detectors at the Electron-Ion Collider
https://github.com/wnma3mz/KD_Notes
Self-supervised Knowledge Distillation Using Singular Value Decomposition
https://github.com/wnn2000/fedaaai
https://github.com/wodyjowski/colab-training
https://github.com/wonbeomjang/Knowledge-Distilling-PyTorch
https://github.com/wonbeomjang/yolov5-knowledge-distillation
Distilling Object Detectors with Fine-grained Feature Imitation
https://github.com/woshisad159/tfnet
Continuous sign language recognition based on cross-resolution knowledge distillation
https://github.com/wsx66848/detection
https://github.com/wutaiqiang/shadow-ft
LLM-Neo: Parameter Efficient Knowledge Distillation for Large Language Models
https://github.com/wuxx1016/Reinforcement-Learning-in-Finance
https://github.com/wuzhiyuan2000/FedAgg
https://github.com/wuzhiyuan2000/FedCache/blob/main/FedCache.py
FedICT: Federated Multi-task Distillation for Multi-access Edge Computing
https://github.com/wyndwarrior/imitation_from_observation
Benchmarking Deep Reinforcement Learning for Continuous Control
https://github.com/xcmyz/FastSpeech
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.