Papers with Code 아카이브

Knowledge Distillation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/NeurAI-Lab/DoGo

공식 코드

Distill on the Go: Online knowledge distillation in self-supervised learning

https://github.com/NickDiSanto/Twitter2030/tree/main/Beta

공식 코드

Transcending the Attention Paradigm: Representation Learning from Geospatial Social Media Data

https://github.com/NiklasTR/oncoassign

공식 코드

A Biologically Plausible Benchmark for Contextual Bandit Algorithms in Precision Oncology Using in vitro Data

https://github.com/Niousha12/Knowledge_Distillation_AD

공식 코드

Multiresolution Knowledge Distillation for Anomaly Detection

https://github.com/NissaFaber/Thesis_repo

공식 코드

Leveraging Foundation Models via Knowledge Distillation in Multi-Object Tracking: Distilling DINOv2 Features to FairMOT

https://github.com/NiuTrans/NiuTrans.NMT

공식 코드

The NiuTrans System for the WMT21 Efficiency Task

https://github.com/NoviScl/AdvRACE

공식 코드

Benchmarking Robustness of Machine Reading Comprehension Models

https://github.com/OPPO-Mente-Lab/PEA-Diffusion

공식 코드

PEA-Diffusion: Parameter-Efficient Adapter with Knowledge Distillation in non-English Text-to-Image Generation

https://github.com/On-Point-RND/SeqNAS

공식 코드

SeqNAS: Neural Architecture Search for Event Sequence Classification

https://github.com/OneClickDeepLearning/classificationOfResidentialRequests

공식 코드

Hybrid Machine Learning Models of Classifying Residential Requests for Smart Dispatching

https://github.com/OpenBioLink/ITO

공식 코드

A global analysis of metrics used for measuring performance in natural language processing

https://github.com/OpenBioLink/OpenBioLink

공식 코드

OpenBioLink: A benchmarking framework for large-scale biomedical link prediction

https://github.com/OpenImagingLab/LenslessFace

공식 코드

LenslessFace: An End-to-End Optimized Lensless System for Privacy-Preserving Face Verification

https://github.com/OptMLGroup/SQN

공식 코드

Quasi-Newton Methods for Machine Learning: Forget the Past, Just Sample

https://github.com/Optimization-AI/LibAUC

공식 코드

LibAUC: A Deep Learning Library for X-Risk Optimization

https://github.com/P2333/Bag-of-Tricks-for-AT

공식 코드

Bag of Tricks for Adversarial Training

https://github.com/PGijsbers/gama

공식 코드

GAMA: a General Automated Machine learning Assistant

https://github.com/PJLallen/D2GPLand

공식 코드

Depth-Driven Geometric Prompt Learning for Laparoscopic Liver Landmark Detection

https://github.com/PMSchulze/NLP-benchmarking

공식 코드

Benchmarking down-scaled (not so large) pre-trained language models

https://github.com/PSCLab-ASU/OpenICS

공식 코드

OpenICS: Open Image Compressive Sensing Toolbox and Benchmark

https://github.com/PV-Lab/Benchmarking

공식 코드

Benchmarking the Performance of Bayesian Optimization across Multiple Experimental Materials Science Domains

https://github.com/PV-Lab/SL-PerovskiteOpt

공식 코드

Machine Learning with Knowledge Constraints for Process Optimization of Open-Air Perovskite Solar Cell Manufacturing

https://github.com/PaddlePaddle/PaddleClas

공식 코드

Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve Backbones

https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-3.0

공식 코드

ERNIE-Tiny : A Progressive Distillation Framework for Pretrained Transformer Compression

https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-tiny

공식 코드

ERNIE 3.0 Tiny: Frustratingly Simple Method to Improve Task-Agnostic Distillation Generalization

https://github.com/PaddlePaddle/PaddleOCR

공식 코드

PP-StructureV2: A Stronger Document Analysis System

https://github.com/PanXiebit/Self-Review-NAT

공식 코드

Infusing Sequential Information into Conditional Masked Translation Model with Self-Review Mechanism

https://github.com/Parry-Parry/ContaminatedDistillation

공식 코드

Training on the Test Model: Contamination in Ranking Distillation

https://github.com/Pascalson/DyKGChat

공식 코드

DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs

https://github.com/PatrickZH/Continual-Representation-Learning-for-Biometric-Identification

공식 코드

Continual Representation Learning for Biometric Identification

https://github.com/PatrykChrabaszcz/Canonical_ES_Atari

공식 코드

Back to Basics: Benchmarking Canonical Evolution Strategies for Playing Atari

https://github.com/Pearl-UTexas/DUST-net

공식 코드

Distributional Depth-Based Estimation of Object Articulation Models

https://github.com/Pearl-UTexas/ScrewNet

공식 코드

ScrewNet: Category-Independent Articulation Model Estimation From Depth Images Using Screw Theory

https://github.com/PengchaoHan/RDSKD

공식 코드

Robustness and Diversity Seeking Data-Free Knowledge Distillation

https://github.com/PhilJd/freiburg_groceries_dataset

공식 코드

The Freiburg Groceries Dataset

https://github.com/PhilippPro/tunability

공식 코드

Tunability: Importance of Hyperparameters of Machine Learning Algorithms

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.