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/amazon-science/e2e-docie
공식 코드REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking
https://github.com/amazon-science/petshop-root-cause-analysis
공식 코드The PetShop Dataset -- Finding Causes of Performance Issues across Microservices
https://github.com/ambekarsameer96/skdcgn
공식 코드SKDCGN: Source-free Knowledge Distillation of Counterfactual Generative Networks using cGANs
https://github.com/ameyagodbole/long-tail-likelihood-splits
공식 코드Benchmarking Long-tail Generalization with Likelihood Splits
https://github.com/amik-tj/dynamic_rectification_knowledge_distillation
공식 코드https://github.com/amink8/folk
공식 코드Frequency-Guided Masking for Enhanced Vision Self-Supervised Learning
https://github.com/amir-ni/trajectory-prediction
공식 코드TrajLearn: Trajectory Prediction Learning using Deep Generative Models
https://github.com/amirmansurian/aicsd
공식 코드AICSD: Adaptive Inter-Class Similarity Distillation for Semantic Segmentation
https://github.com/amnondrory/lidarregistration
공식 코드https://github.com/amr-keleg/dlama
공식 코드https://github.com/amrinkareem/paris3d
공식 코드PARIS3D: Reasoning-based 3D Part Segmentation Using Large Multimodal Model
https://github.com/amzn/emukit
공식 코드https://github.com/anapplecore/mose
공식 코드https://github.com/andiva/tmpnn
공식 코드TMPNN: High-Order Polynomial Regression Based on Taylor Map Factorization
https://github.com/andotalao24/multistage-collaborative-knowledge-distillation
공식 코드https://github.com/andreea-glavan/multimodal-audiovisual-scene-recognition
공식 코드InstaIndoor and Multi-modal Deep Learning for Indoor Scene Recognition
https://github.com/andreeaiana/nemig
공식 코드NeMig -- A Bilingual News Collection and Knowledge Graph about Migration
https://github.com/andreeaiana/newsreclib
공식 코드NewsRecLib: A PyTorch-Lightning Library for Neural News Recommendation
https://github.com/andrepugni/esc
공식 코드https://github.com/andreskarjus/machineassistedmixedmethods
공식 코드https://github.com/andreyrisukhin/colorgrid
공식 코드ColorGrid: A Multi-Agent Non-Stationary Environment for Goal Inference and Assistance
https://github.com/andygr/ml-classification
공식 코드https://github.com/andygr/ml-regression
공식 코드https://github.com/andyisokay/delta-influence
공식 코드https://github.com/andyreagan/sentiment-analysis-comparison
공식 코드https://github.com/angushuang17/corr_www
공식 코드https://github.com/angusmaiden/complex-fer
공식 코드Complex Facial Expression Recognition Using Deep Knowledge Distillation of Basic Features
https://github.com/aniket004/bri3l
공식 코드https://github.com/aniketrege/cure-bench
공식 코드CuRe: Cultural Gaps in the Long Tail of Text-to-Image Systems
https://github.com/anira-project/anira
공식 코드ANIRA: An Architecture for Neural Network Inference in Real-Time Audio Applications
https://github.com/anjany/verse
공식 코드https://github.com/ankilab/spoken-100
공식 코드https://github.com/anmolchaure/climate_emulators
공식 코드Finding the Perfect Fit: Applying Regression Models to ClimateBench v1.0
https://github.com/anon-user-for-web/badlad
공식 코드BaDLAD: A Large Multi-Domain Bengali Document Layout Analysis Dataset
https://github.com/anonno2/crosstalk-generation
공식 코드Can Language Models Make Fun? A Case Study in Chinese Comical Crosstalk
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.