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/ccp-eva/sporttaskme22

공식 코드

Sport Task: Fine Grained Action Detection and Classification of Table Tennis Strokes from Videos for MediaEval 2022

https://github.com/cecnl/eeg-kd

공식 코드

Enhancing Low-Density EEG-Based Brain-Computer Interfaces with Similarity-Keeping Knowledge Distillation

https://github.com/cemos-is/genformer

공식 코드

GenFormer -- Generated Images are All You Need to Improve Robustness of Transformers on Small Datasets

https://github.com/cemos-is/robust-minisets

공식 코드

GenFormer -- Generated Images are All You Need to Improve Robustness of Transformers on Small Datasets

https://github.com/cemuluoglakci/hypotermqa

공식 코드

HypoTermQA: Hypothetical Terms Dataset for Benchmarking Hallucination Tendency of LLMs

https://github.com/cevers/sap_locata_eval

공식 코드

The LOCATA Challenge: Acoustic Source Localization and Tracking

https://github.com/cf020031308/gem

공식 코드

Graph Entropy Minimization for Semi-supervised Node Classification

https://github.com/cgoliver/rnaglib

공식 코드

A Comprehensive Benchmark for RNA 3D Structure-Function Modeling

https://github.com/cgye96/a_closer_look_at_3dfsl

공식 코드

What Makes for Effective Few-shot Point Cloud Classification?

https://github.com/chaitjo/efficient-gnns

공식 코드

On Representation Knowledge Distillation for Graph Neural Networks

https://github.com/chakkritte/SalNAS

공식 코드

SalNAS: Efficient Saliency-prediction Neural Architecture Search with self-knowledge distillation

https://github.com/chakra-et/chakra

공식 코드

Chakra: Advancing Performance Benchmarking and Co-design using Standardized Execution Traces

https://github.com/chandar-lab/subgoal_distillation_llm

공식 코드

Sub-goal Distillation: A Method to Improve Small Language Agents

https://github.com/changlin31/DNA

공식 코드

Blockwisely Supervised Neural Architecture Search with Knowledge Distillation

https://github.com/chao1224/geom3d

공식 코드

Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materials

https://github.com/chaoningzhang/mobilesam

공식 코드

MobileSAMv2: Faster Segment Anything to Everything

https://github.com/charlesgong12/rece

공식 코드

Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models

https://github.com/charsyme/Human-Data-Generation-Framework

공식 코드

Efficient Realistic Data Generation Framework leveraging Deep Learning-based Human Digitization

https://github.com/chartgalaxy/chartgalaxy

공식 코드

ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation

https://github.com/chasonjiang/fscilss

공식 코드

Few-shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation

https://github.com/chelsea234/hifi_ifdl

공식 코드

DeepFake-O-Meter v2.0: An Open Platform for DeepFake Detection

https://github.com/chen700564/RGB

공식 코드

Benchmarking Large Language Models in Retrieval-Augmented Generation

https://github.com/chencn2020/mobileiqa

공식 코드

MobileIQA: Exploiting Mobile-level Diverse Opinion Network For No-Reference Image Quality Assessment Using Knowledge Distillation

https://github.com/cheneydon/efficient-bert

공식 코드

EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation

https://github.com/cheneydon/hrkd

공식 코드

HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model Compression

https://github.com/chenfei-liao/multi-modal-semantic-segmentation-robustness-benchmark

공식 코드

Benchmarking Multi-modal Semantic Segmentation under Sensor Failures: Missing and Noisy Modality Robustness

https://github.com/chengang95/unkd

공식 코드

Unbiased Knowledge Distillation for Recommendation

https://github.com/chengcv/dfrfs

공식 코드

Disentangled Feature Representation for Few-shot Image Classification

https://github.com/chenguolin/InstructScene

공식 코드

InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior

https://github.com/chengxuphd/dcr

공식 코드

DCR: Quantifying Data Contamination in LLMs Evaluation

https://github.com/chengyuehuang511/frames-vqa

공식 코드

FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering

https://github.com/chengyui/nuwats

공식 코드

NuwaTS: a Foundation Model Mending Every Incomplete Time Series

https://github.com/chengyuyang-njit/imagedesmoke

공식 코드

Laparoscopic Image Desmoking Using the U-Net with New Loss Function and Integrated Differentiable Wiener Filter

https://github.com/chengzhang-98/lqer

공식 코드

LQER: Low-Rank Quantization Error Reconstruction for LLMs

https://github.com/chenhongyiyang/pgd

공식 코드

Prediction-Guided Distillation for Dense Object Detection

https://github.com/chenjzbuaa/satir

공식 코드

Learning to "Segment Anything" in Thermal Infrared Images through Knowledge Distillation with a Large Scale Dataset SATIR

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