Papers with Code 아카이브
Knowledge Distillation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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/bigD233/AMFD
공식 코드AMFD: Distillation via Adaptive Multimodal Fusion for Multispectral Pedestrian Detection
https://github.com/bigaidream-projects/role-kd
공식 코드https://github.com/bigcode-project/bigcodebench
공식 코드BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions
https://github.com/bigcode-project/bigcodebench-annotation
공식 코드BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions
https://github.com/bigdata-graph/gmvit
공식 코드Group Multi-View Transformer for 3D Shape Analysis with Spatial Encoding
https://github.com/bigdata-inha/Pool-of-Experts-code
공식 코드Pool of Experts: Realtime Querying Specialized Knowledge in Massive Neural Networks
https://github.com/bigdata-inha/Split-and-Bridge
공식 코드Split-and-Bridge: Adaptable Class Incremental Learning within a Single Neural Network
https://github.com/bigdata-inha/ta-dfkd-official
공식 코드Teacher as a Lenient Expert: Teacher-Agnostic Data-Free Knowledge Distillation
https://github.com/bigheiniu/mend
공식 코드MEND: Meta dEmonstratioN Distillation for Efficient and Effective In-Context Learning
https://github.com/bigml-cs-ucla/mkdt
공식 코드https://github.com/bigml-cs-ucla/spuco
공식 코드https://github.com/bigscience-workshop/promptsource
공식 코드Multitask Prompted Training Enables Zero-Shot Task Generalization
https://github.com/bigscience-workshop/t-zero
공식 코드Multitask Prompted Training Enables Zero-Shot Task Generalization
https://github.com/bilaltalha/sip-17
공식 코드Towards Sim-to-Real Industrial Parts Classification with Synthetic Dataset
https://github.com/billhhh/MCKD
공식 코드https://github.com/billpsomas/efficient-probing
공식 코드Attention, Please! Revisiting Attentive Probing for Masked Image Modeling
https://github.com/bimib-disco/og-space
공식 코드OG-SPACE: Optimized Stochastic Simulation of Spatial Models of Cancer Evolution
https://github.com/bimsbbioinfo/pocketvina
공식 코드https://github.com/binghaolu/kd-msi
공식 코드Weakly Supervised Change Detection via Knowledge Distillation and Multiscale Sigmoid Inference
https://github.com/bingqingcheng/linear-regression-benchmarks
공식 코드https://github.com/binwang28/evalrank-embedding-evaluation
공식 코드Just Rank: Rethinking Evaluation with Word and Sentence Similarities
https://github.com/bio-nlp/medqa-cs
공식 코드MedQA-CS: Benchmarking Large Language Models Clinical Skills Using an AI-SCE Framework
https://github.com/biochunan/asep-dataset
공식 코드AsEP: Benchmarking Deep Learning Methods for Antibody-specific Epitope Prediction
https://github.com/biocypher/biochatter-light
공식 코드A Platform for the Biomedical Application of Large Language Models
https://github.com/biocypher/chatgse
공식 코드A Platform for the Biomedical Application of Large Language Models
https://github.com/biomedia-mbzuai/dynammo
공식 코드DynaMMo: Dynamic Model Merging for Efficient Class Incremental Learning for Medical Images
https://github.com/biomedia-mbzuai/fetalclip
공식 코드FetalCLIP: A Visual-Language Foundation Model for Fetal Ultrasound Image Analysis
https://github.com/biomedicalinformaticsgroup/gnn-suite
공식 코드GNN-Suite: a Graph Neural Network Benchmarking Framework for Biomedical Informatics
https://github.com/biomedsciai/biomed-multi-omic
공식 코드BMFM-RNA: An Open Framework for Building and Evaluating Transcriptomic Foundation Models
https://github.com/biomedsciai/gene-benchmark
공식 코드Does your model understand genes? A benchmark of gene properties for biological and text models
https://github.com/bionlproc/twitter-covid-qa-extraction
공식 코드COVID-19 event extraction from Twitter via extractive question answering with continuous prompts
https://github.com/bit-ml/avh-align
공식 코드Circumventing shortcuts in audio-visual deepfake detection datasets with unsupervised learning
https://github.com/bladedancer957/finer
공식 코드https://github.com/bliss-e-v/scam
공식 코드SCAM: A Real-World Typographic Robustness Evaluation for Multimodal Foundation Models
https://github.com/blutjens/climate-emulator
공식 코드The impact of internal variability on benchmarking deep learning climate emulators
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.