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/jhoon-oh/kd_data

공식 코드

Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation

https://github.com/jhu-clsp/analogical-reasoning

공식 코드

AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogies

https://github.com/jhuang81/weak-sup-visual-grounding

공식 코드

Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation

https://github.com/ji-cather/graphagent

공식 코드

LLM-Based Multi-Agent Systems are Scalable Graph Generative Models

https://github.com/jia-py/erase

공식 코드

ERASE: Benchmarking Feature Selection Methods for Deep Recommender Systems

https://github.com/jiachens/ModelNet40-C

공식 코드

Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions

https://github.com/jiachenwestlake/MMKD

공식 코드

Adversarial Moment-Matching Distillation of Large Language Models

https://github.com/jiaconghu/model-lego

공식 코드

Model LEGO: Creating Models Like Disassembling and Assembling Building Blocks

https://github.com/jiahao004/distillcse

공식 코드

DistillCSE: Distilled Contrastive Learning for Sentence Embeddings

https://github.com/jiangjyjy/yue-benchmark

공식 코드

How Well Do LLMs Handle Cantonese? Benchmarking Cantonese Capabilities of Large Language Models

https://github.com/jiangpenghe/cl-lora

공식 코드

CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning

https://github.com/jianhao2016/AllSet

공식 코드

You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks

https://github.com/jianlong-yuan/fakd

공식 코드

FAKD: Feature Augmented Knowledge Distillation for Semantic Segmentation

https://github.com/jianlong-yuan/semi-mmseg

공식 코드

Semi-supervised Semantic Segmentation with Mutual Knowledge Distillation

https://github.com/jiany-ctrl/Crossmodal-KD-for-Vision-to-Sensor-HAR

공식 코드

Cross-modal Knowledge Distillation for Vision-to-Sensor Action Recognition

https://github.com/jianzeli-114/dfosd

공식 코드

Distillation-Free One-Step Diffusion for Real-World Image Super-Resolution

https://github.com/jianzhangcs/r-dfcil

공식 코드

R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning

https://github.com/jiarunliu/biovfm

공식 코드

BioVFM-21M: Benchmarking and Scaling Self-Supervised Vision Foundation Models for Biomedical Image Analysis

https://github.com/jiawei-ren/modelnetc

공식 코드

Benchmarking and Analyzing Point Cloud Classification under Corruptions

https://github.com/jiaweilian/ap-pa

공식 코드

Benchmarking Adversarial Patch Against Aerial Detection

https://github.com/jiaweilian/benchmarking_physical_attack

공식 코드

PADetBench: Towards Benchmarking Physical Attacks against Object Detection

https://github.com/jiaweilian/padetbench

공식 코드

PADetBench: Towards Benchmarking Physical Attacks against Object Detection

https://github.com/jiehonglin/vi-net

공식 코드

VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representations

https://github.com/jiequancui/DKL

공식 코드

Decoupled Kullback-Leibler Divergence Loss

https://github.com/jieyibi/amdkd

공식 코드

Learning Generalizable Models for Vehicle Routing Problems via Knowledge Distillation

https://github.com/jihoontack/SiMT

공식 코드

Meta-Learning with Self-Improving Momentum Target

https://github.com/jihyukkim-nlp/CollectiveKD

공식 코드

Collective Relevance Labeling for Passage Retrieval

https://github.com/jimmylihui/OpenGenome

공식 코드

GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models

https://github.com/jind11/HSLN-Joint-Sentence-Classification

공식 코드

Hierarchical Neural Networks for Sequential Sentence Classification in Medical Scientific Abstracts

https://github.com/jindongwang/transferlearning

공식 코드

Domain-invariant Feature Exploration for Domain Generalization

https://github.com/jinfengx/pointcloudpdf

공식 코드

PDF: A Probability-Driven Framework for Open World 3D Point Cloud Semantic Segmentation

https://github.com/jing-ds/hnn_gad

공식 코드

Three Revisits to Node-Level Graph Anomaly Detection: Outliers, Message Passing and Hyperbolic Neural Networks

https://github.com/jingcheng-du/ML_Net-1

공식 코드

ML-Net: multi-label classification of biomedical texts with deep neural networks

https://github.com/jinghe-mel/ufen-slam

공식 코드

Knowledge Distillation for Feature Extraction in Underwater VSLAM

https://github.com/jingkang50/openood

공식 코드

OpenOOD: Benchmarking Generalized Out-of-Distribution Detection

https://github.com/jinglin-liang/dddr

공식 코드

Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning

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