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/spaghettiSystems/serval

공식 코드

SER Evals: In-domain and Out-of-domain Benchmarking for Speech Emotion Recognition

https://github.com/spalabucr/pategan-audit

공식 코드

The Elusive Pursuit of Reproducing PATE-GAN: Benchmarking, Auditing, Debugging

https://github.com/sparisi/visit-value-explore

공식 코드

Long-Term Visitation Value for Deep Exploration in Sparse Reward Reinforcement Learning

https://github.com/spbu-lipengyi/dkdl-net

공식 코드

DKDL-Net: A Lightweight Bearing Fault Detection Model via Decoupled Knowledge Distillation and Low-Rank Adaptation Fine-tuning

https://github.com/spcl/mrag

공식 코드

Multi-Head RAG: Solving Multi-Aspect Problems with LLMs

https://github.com/sphere-ai-lab/formalmath-bench

공식 코드

FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models

https://github.com/spiral-med/diagnosisarena

공식 코드

DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models

https://github.com/spotify-research/tot

공식 코드

When the Music Stops: Tip-of-the-Tongue Retrieval for Music

https://github.com/spring-epfl/iccwd

공식 코드

A Manually Annotated Image-Caption Dataset for Detecting Children in the Wild

https://github.com/sprinter1999/fnbench

공식 코드

FNBench: Benchmarking Robust Federated Learning against Noisy Labels

https://github.com/squareroot3/gadbench

공식 코드

GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detection

https://github.com/squareroot3/grapharena

공식 코드

GraphArena: Benchmarking Large Language Models on Graph Computational Problems

https://github.com/sri-karthik-avala/capsule-challenge-2024

공식 코드

Capsule Vision 2024 Challenge: Multi-Class Abnormality Classification for Video Capsule Endoscopy

https://github.com/sridharsola/msd-e

공식 코드

Masked Student Dataset of Expressions

https://github.com/srikarym/CCTV-Gun

공식 코드

CCTV-Gun: Benchmarking Handgun Detection in CCTV Images

https://github.com/ssarfraz/QuoVadisTAD

공식 코드

Position: Quo Vadis, Unsupervised Time Series Anomaly Detection?

https://github.com/sseung0703/Knowledge_distillation_via_TF2.0

공식 코드

Graph-based Knowledge Distillation by Multi-head Attention Network

https://github.com/sseung0703/SSKD

공식 코드

Self-supervised Knowledge Distillation Using Singular Value Decomposition

https://github.com/sseung0703/SSKD_SVD

공식 코드

Self-supervised Knowledge Distillation Using Singular Value Decomposition

https://github.com/sseung0703/ekg

공식 코드

Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter Pruning

https://github.com/ssskj/herolt

공식 코드

Towards Heterogeneous Long-tailed Learning: Benchmarking, Metrics, and Toolbox

https://github.com/ssydasheng/predictive-correlation-benchmark

공식 코드

Beyond Marginal Uncertainty: How Accurately can Bayesian Regression Models Estimate Posterior Predictive Correlations?

https://github.com/stacs-cp/autoig

공식 코드

A Framework for Generating Informative Benchmark Instances

https://github.com/stanford-crfm/helm

공식 코드

Image2Struct: Benchmarking Structure Extraction for Vision-Language Models

https://github.com/stanfordmlgroup/CheXseg

공식 코드

CheXseg: Combining Expert Annotations with DNN-generated Saliency Maps for X-ray Segmentation

https://github.com/stanfordmlgroup/cheXphoto

공식 코드

CheXphoto: 10,000+ Photos and Transformations of Chest X-rays for Benchmarking Deep Learning Robustness

https://github.com/stanfordmlgroup/medagentbench

공식 코드

MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents

https://github.com/staoxiao/libvq

공식 코드

Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense Embeddings

https://github.com/star-center/ros_mp4

공식 코드

High-Quality, ROS Compatible Video Encoding and Decoding for High-Definition Datasets

https://github.com/statsmerging/statsmerging

공식 코드

StatsMerging: Statistics-Guided Model Merging via Task-Specific Teacher Distillation

https://github.com/stavrosorf/ev2gym

공식 코드

EV2Gym: A Flexible V2G Simulator for EV Smart Charging Research and Benchmarking

https://github.com/stefanosantaris/DMTKG

공식 코드

Distill2Vec: Dynamic Graph Representation Learning with Knowledge Distillation

https://github.com/stegmaierj/CellSynthesis

공식 코드

3D fluorescence microscopy data synthesis for segmentation and benchmarking

https://github.com/stepjam/ARM

공식 코드

Coarse-to-Fine Q-attention with Learned Path Ranking

https://github.com/stepmat/ContinuousInformationGain

공식 코드

A Continuous Information Gain Measure to Find the Most Discriminatory Problems for AI Benchmarking

https://github.com/stern5497/doc2docbeirir

공식 코드

One Law, Many Languages: Benchmarking Multilingual Legal Reasoning for Judicial Support

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