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/tmehari/ssm_ecg

공식 코드

Towards quantitative precision for ECG analysis: Leveraging state space models, self-supervision and patient metadata

https://github.com/tmtuan1307/nayer

공식 코드

NAYER: Noisy Layer Data Generation for Efficient and Effective Data-free Knowledge Distillation

https://github.com/tnresearch/forlorn

공식 코드

FORLORN: A Framework for Comparing Offline Methods and Reinforcement Learning for Optimization of RAN Parameters

https://github.com/tobideusser/kpi-edgar

공식 코드

KPI-EDGAR: A Novel Dataset and Accompanying Metric for Relation Extraction from Financial Documents

https://github.com/tobischimanski/climretrieve

공식 코드

ClimRetrieve: A Benchmarking Dataset for Information Retrieval from Corporate Climate Disclosures

https://github.com/tofis/human4d_dataset

공식 코드

HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Media

https://github.com/tomsheng21/adaptguard

공식 코드

AdaptGuard: Defending Against Universal Attacks for Model Adaptation

https://github.com/tonytan48/kd-docre

공식 코드

Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation

https://github.com/tonyzhou98/long_tail_kd

공식 코드

Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation

https://github.com/townim-faisal/lwf-3D

공식 코드

Learning without Forgetting for 3D Point Cloud Objects

https://github.com/tqwei05/PlantSeg

공식 코드

PlantSeg: A Large-Scale In-the-wild Dataset for Plant Disease Segmentation

https://github.com/tqzhong/cg4mctg

공식 코드

Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation

https://github.com/trais-lab/dattri

공식 코드

$\texttt{dattri}$: A Library for Efficient Data Attribution

https://github.com/transmuteai/data-efficient-transformers

공식 코드

Data-Efficient Training of CNNs and Transformers with Coresets: A Stability Perspective

https://github.com/trevormcinroe/pixelbrax

공식 코드

PixelBrax: Learning Continuous Control from Pixels End-to-End on the GPU

https://github.com/trianam/quantumNoiseClassification

공식 코드

Machine learning classification of non-Markovian noise disturbing quantum dynamics

https://github.com/trinhvg/moma

공식 코드

MoMA: Momentum Contrastive Learning with Multi-head Attention-based Knowledge Distillation for Histopathology Image Analysis

https://github.com/trougnouf/nind-denoise

공식 코드

Natural Image Noise Dataset

https://github.com/trustairlab/hatebench

공식 코드

HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns

https://github.com/trusthlt/legal-argument-reasoning-task

공식 코드

The Legal Argument Reasoning Task in Civil Procedure

https://github.com/tsafavi/codex

공식 코드

CoDEx: A Comprehensive Knowledge Graph Completion Benchmark

https://github.com/tsattler/visuallocalizationbenchmark

공식 코드

Reference Pose Generation for Long-term Visual Localization via Learned Features and View Synthesis

https://github.com/tsinghua-fib-lab/moss

공식 코드

A GPU-accelerated Large-scale Simulator for Transportation System Optimization Benchmarking

https://github.com/tsj-001/aaai24-gkt

공식 코드

Boosting Residual Networks with Group Knowledge

https://github.com/ttttttris/bebert

공식 코드

BEBERT: Efficient and Robust Binary Ensemble BERT

https://github.com/tu184044109/VIDEVAL_release

공식 코드

UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content

https://github.com/tue-mps/benchmark-vfm-ss

공식 코드

How to Benchmark Vision Foundation Models for Semantic Segmentation?

https://github.com/tulerfeng/PlanKD

공식 코드

On the Road to Portability: Compressing End-to-End Motion Planner for Autonomous Driving

https://github.com/tum-ei-eda/mlonmcu

공식 코드

MLonMCU: TinyML Benchmarking with Fast Retargeting

https://github.com/tum-pbs/autoreg-pde-diffusion

공식 코드

Benchmarking Autoregressive Conditional Diffusion Models for Turbulent Flow Simulation

https://github.com/tumaer/lagrangebench

공식 코드

LagrangeBench: A Lagrangian Fluid Mechanics Benchmarking Suite

https://github.com/tumbais/dynamicneighborhoodconstruction

공식 코드

Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces

https://github.com/tumcps/commonpower

공식 코드

CommonPower: A Framework for Safe Data-Driven Smart Grid Control

https://github.com/tumlegaltech/lexsumm-lext5

공식 코드

LexSumm and LexT5: Benchmarking and Modeling Legal Summarization Tasks in English

https://github.com/turuibo/cautabbench

공식 코드

Causality for Tabular Data Synthesis: A High-Order Structure Causal Benchmark Framework

https://github.com/twangnh/Distilling-Object-Detectors

공식 코드

Distilling Object Detectors with Fine-grained Feature Imitation

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