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/aioz-ai/BMVC20_CBSwR

공식 코드

Deep Metric Learning Meets Deep Clustering: An Novel Unsupervised Approach for Feature Embedding

https://github.com/aioz-ai/ICCV19_VQA-CTI

공식 코드

Compact Trilinear Interaction for Visual Question Answering

https://github.com/aipmlab/kd-fmv

공식 코드

A Knowledge Distillation-Based Approach to Enhance Transparency of Classifier Models

https://github.com/airaria/TextBrewer

공식 코드

TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language Processing

https://github.com/airaria/grain

공식 코드

Gradient-based Intra-attention Pruning on Pre-trained Language Models

https://github.com/airi-institute/pogema

공식 코드

POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding

https://github.com/aistairc/RDF-star2Vec

공식 코드

RDF-star2Vec: RDF-star Graph Embeddings for Data Mining

https://github.com/aistairc/kgrc-rdf-star

공식 코드

RDF-star2Vec: RDF-star Graph Embeddings for Data Mining

https://github.com/aistairc/vhakg-tools

공식 코드

VHAKG: A Multi-modal Knowledge Graph Based on Synchronized Multi-view Videos of Daily Activities

https://github.com/aistairc/virtualhome_aist

공식 코드

VHAKG: A Multi-modal Knowledge Graph Based on Synchronized Multi-view Videos of Daily Activities

https://github.com/aitsc/glmkd

공식 코드

Are Intermediate Layers and Labels Really Necessary? A General Language Model Distillation Method

https://github.com/aizazsharif/benchmarking-qrs-2022

공식 코드

Evaluating the Robustness of Deep Reinforcement Learning for Autonomous Policies in a Multi-agent Urban Driving Environment

https://github.com/ajay-pratap-singh-518/Capsule-Vision-2024-challenge

공식 코드

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

https://github.com/ajaysub110/satbench

공식 코드

SATBench: Benchmarking the speed-accuracy tradeoff in object recognition by humans and dynamic neural networks

https://github.com/akideliu/bpkd

공식 코드

BPKD: Boundary Privileged Knowledge Distillation For Semantic Segmentation

https://github.com/aksw/llm-kg-bench

공식 코드

Developing a Scalable Benchmark for Assessing Large Language Models in Knowledge Graph Engineering

https://github.com/aksw/llm-kg-bench-results

공식 코드

Developing a Scalable Benchmark for Assessing Large Language Models in Knowledge Graph Engineering

https://github.com/alan-turing-institute/mlaut

공식 코드

Machine Learning Automation Toolbox (MLaut)

https://github.com/aleflabo/prego

공식 코드

PREGO: online mistake detection in PRocedural EGOcentric videos

https://github.com/aleksispi/ml-cloud-opt-thick

공식 코드

Creating and Leveraging a Synthetic Dataset of Cloud Optical Thickness Measures for Cloud Detection in MSI

https://github.com/alephzr/ie-gan

공식 코드

IE-GAN: An Improved Evolutionary Generative Adversarial Network Using a New Fitness Function and a Generic Crossover Operator

https://github.com/alevine0/reengage

공식 코드

Goal-Conditioned Q-Learning as Knowledge Distillation

https://github.com/alexa/Topical-Chat

공식 코드

Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations

https://github.com/alexanderhberger/topo-pitfalls

공식 코드

Pitfalls of topology-aware image segmentation

https://github.com/alexandrosstergiou/adaPool

공식 코드

AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling

https://github.com/alexbeesonwarwick/offlinerlconstrainedensemble

공식 코드

Balancing policy constraint and ensemble size in uncertainty-based offline reinforcement learning

https://github.com/alexeyev/kyrgyz-multi-label-topic-classification

공식 코드

Benchmarking Multilabel Topic Classification in the Kyrgyz Language

https://github.com/alexklwong/mondi-python

공식 코드

Monitored Distillation for Positive Congruent Depth Completion

https://github.com/alextxu/ckd

공식 코드

Comparative Knowledge Distillation

https://github.com/algoprog/InteRank

공식 코드

Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking

https://github.com/ali-forootani/compactformer

공식 코드

Synthetic Time Series Forecasting with Transformer Architectures: Extensive Simulation Benchmarks

https://github.com/alibaba-miil/headsharingkd

공식 코드

It's All in the Head: Representation Knowledge Distillation through Classifier Sharing

https://github.com/alibaba-miil/solving_imagenet

공식 코드

Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results

https://github.com/alibaba-nlp/ibkd

공식 코드

Text Representation Distillation via Information Bottleneck Principle

https://github.com/alibaba-nlp/omnisearch

공식 코드

Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent

https://github.com/alibaba-nlp/webwalker

공식 코드

WebWalker: Benchmarking LLMs in Web Traversal

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