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/mahmad00/disjoint-sampling-for-hyperspectral-image-classification
공식 코드https://github.com/mahmoodlab/hest
공식 코드HEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis
https://github.com/mahmoodlab/patho-bench
공식 코드https://github.com/mahmoodlab/trident
공식 코드https://github.com/maho3/ltu-ili
공식 코드LtU-ILI: An All-in-One Framework for Implicit Inference in Astrophysics and Cosmology
https://github.com/mahsa91/GKD
공식 코드GKD: Semi-supervised Graph Knowledge Distillation for Graph-Independent Inference
https://github.com/mail-ecnu/text-gym-agents
공식 코드Can language agents be alternatives to PPO? A Preliminary Empirical Study On OpenAI Gym
https://github.com/mainlp/how-to-distill-your-bert
공식 코드https://github.com/maitrix-org/de-arena
공식 코드Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models
https://github.com/majitao-xd/stad-had
공식 코드Exploring Hyperspectral Anomaly Detection with Human Vision: A Small Target Aware Detector
https://github.com/makstarnavskyi/gector-large
공식 코드Ensembling and Knowledge Distilling of Large Sequence Taggers for Grammatical Error Correction
https://github.com/mala-lab/opencil
공식 코드OpenCIL: Benchmarking Out-of-Distribution Detection in Class-Incremental Learning
https://github.com/mala-lab/sic-cads
공식 코드Simple Image-level Classification Improves Open-vocabulary Object Detection
https://github.com/malikmtahir/epi
공식 코드https://github.com/mandyyyyii/scibench
공식 코드SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models
https://github.com/manga-uofa/fdistill
공식 코드f-Divergence Minimization for Sequence-Level Knowledge Distillation
https://github.com/manjahdani/csbad
공식 코드Camera clustering for scalable stream-based active distillation
https://github.com/mansoor-at/semi-supervised-surgical-tool-detection
공식 코드A semi-supervised Teacher-Student framework for surgical tool detection and localization
https://github.com/maorash/nern
공식 코드https://github.com/maoyj1998/transdic
공식 코드https://github.com/maoyunyao/cmd
공식 코드CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation
https://github.com/marcelsheeny/radiate_sdk
공식 코드RADIATE: A Radar Dataset for Automotive Perception in Bad Weather
https://github.com/marcovirgolin/GP-GOMEA
공식 코드Contemporary Symbolic Regression Methods and their Relative Performance
https://github.com/marct0k/franck
공식 코드Fedivertex: a Graph Dataset based on Decentralized Social Networks for Trustworthy Machine Learning
https://github.com/marialaurasantoni/diversity-fitness
공식 코드Illuminating the Diversity-Fitness Trade-Off in Black-Box Optimization
https://github.com/marieoestreich/pro-gene-gen
공식 코드Towards Biologically Plausible and Private Gene Expression Data Generation
https://github.com/mariotheone/gretel
공식 코드https://github.com/markus93/fit-on-the-test
공식 코드On the Usefulness of the Fit-on-the-Test View on Evaluating Calibration of Classifiers
https://github.com/markywg/transagent
공식 코드TransAgent: Transfer Vision-Language Foundation Models with Heterogeneous Agent Collaboration
https://github.com/maroo-sky/fsd
공식 코드Feature Structure Distillation with Centered Kernel Alignment in BERT Transferring
https://github.com/marrlab/domainlab
공식 코드DomainLab: A modular Python package for domain generalization in deep learning
https://github.com/marsggbo/CovidNet3D
공식 코드https://github.com/marsjacobs/kd-qat-large-enc
공식 코드https://github.com/marsjacobs/ti-kd-qat
공식 코드https://github.com/martinbeseda/steady-state
공식 코드A Kernel-Based Approach for Accurate Steady-State Detection in Performance Time Series
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.