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/ryojitanabe/largebbob2022

공식 코드

Benchmarking the Hooke-Jeeves Method, MTS-LS1, and BSrr on the Large-scale BBOB Function Set

https://github.com/ryojitanabe/prefqi

공식 코드

Quality Indicators for Preference-based Evolutionary Multi-objective Optimization Using a Reference Point: A Review and Analysis

https://github.com/s3prl/s3prl

공식 코드

S3PRL-VC: Open-source Voice Conversion Framework with Self-supervised Speech Representations

https://github.com/saattrupdan/scandeval

공식 코드

ScandEval: A Benchmark for Scandinavian Natural Language Processing

https://github.com/sabagh1994/pgvae

공식 코드

Robust Model-Based Optimization for Challenging Fitness Landscapes

https://github.com/sadjadeb/exHarmony

공식 코드

exHarmony: Authorship and Citations for Benchmarking the Reviewer Assignment Problem

https://github.com/saeed-anwar/ColorSurvey

공식 코드

Image Colorization: A Survey and Dataset

https://github.com/safolab-wisc/fiubench

공식 코드

Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset

https://github.com/safolab-wisc/injecguard

공식 코드

InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

https://github.com/sahibsin/DP_DeepLearning_Pneumonia

공식 코드

Benchmarking Differentially Private Residual Networks for Medical Imagery

https://github.com/sahoonihar/indibias

공식 코드

IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Context

https://github.com/saic-fi/sslight

공식 코드

Effective Self-supervised Pre-training on Low-compute Networks without Distillation

https://github.com/sail-sg/mmcbench

공식 코드

Benchmarking Large Multimodal Models against Common Corruptions

https://github.com/sail-sg/offbench

공식 코드

Improving and Benchmarking Offline Reinforcement Learning Algorithms

https://github.com/sailab-code/SAIFooler

공식 코드

Messing Up 3D Virtual Environments: Transferable Adversarial 3D Objects

https://github.com/sainzerjj/sferd

공식 코드

Reducing Spatial Fitting Error in Distillation of Denoising Diffusion Models

https://github.com/sakharok13/x-ray-teacher-patching-tools

공식 코드

Weak-to-Strong 3D Object Detection with X-Ray Distillation

https://github.com/sakurajimamaiii/protokd

공식 코드

Prototype Knowledge Distillation for Medical Segmentation with Missing Modality

https://github.com/salah-zaiem/speechbrain-2

공식 코드

Speech Self-Supervised Representation Benchmarking: Are We Doing it Right?

https://github.com/salesforce/bolaa

공식 코드

BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents

https://github.com/salesforce/lavis

공식 코드

LAVIS: A Library for Language-Vision Intelligence

https://github.com/salesforce/nonauto-nmt

공식 코드

Non-Autoregressive Neural Machine Translation

https://github.com/salesforceairesearch/crmarena

공식 코드

CRMArena-Pro: Holistic Assessment of LLM Agents Across Diverse Business Scenarios and Interactions

https://github.com/salmank255/ROAD_Waymo_Baseline

공식 코드

ROAD-Waymo: Action Awareness at Scale for Autonomous Driving

https://github.com/salmon1802/ektf

공식 코드

Ensemble Learning via Knowledge Transfer for CTR Prediction

https://github.com/samchevalier/dcattack

공식 코드

Identifying the Smallest Adversarial Load Perturbations that Render DC-OPF Infeasible

https://github.com/sameerkhanna786/cvueba

공식 코드

Using Color To Identify Insider Threats

https://github.com/samia067/crisp

공식 코드

CriSp: Leveraging Tread Depth Maps for Enhanced Crime-Scene Shoeprint Matching

https://github.com/samia067/shoerinsics

공식 코드

Creating a Forensic Database of Shoeprints from Online Shoe Tread Photos

https://github.com/samiraabnar/Reflect

공식 코드

Transferring Inductive Biases through Knowledge Distillation

https://github.com/samjia2000/optimal-reasoning-efficiency

공식 코드

How Far Are We from Optimal Reasoning Efficiency?

https://github.com/samuelepapa/fit-a-nef

공식 코드

How to Train Neural Field Representations: A Comprehensive Study and Benchmark

https://github.com/samuelstanton/gnosis

공식 코드

Does Knowledge Distillation Really Work?

https://github.com/sangyun884/rfpp

공식 코드

Improving the Training of Rectified Flows

https://github.com/sanjaykariyappa/maze

공식 코드

MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation

https://github.com/sanmin0312/labeldistill

공식 코드

LabelDistill: Label-guided Cross-modal Knowledge Distillation for Camera-based 3D Object Detection

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