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/zeroxleo/ml-agent
MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation
https://github.com/zezhishao/d2stgnn
https://github.com/zezhishao/step
https://github.com/zh320/realtime-semantic-segmentation-pytorch
https://github.com/zhangbo2008/fastSpeeck2_chinese_train
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/zhanggefan/mmdet-yolov4
https://github.com/zhanghanbo/invig-dataset
InViG: Benchmarking Interactive Visual Grounding with 500K Human-Robot Interactions
https://github.com/zhangxu0963/npc
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/zhaochenyang20/Prompt2Model-Self-Guide
Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks
https://github.com/zhaoyang97/mmdetection
https://github.com/zhichao-aws/opensearch-sparse-model-tuning-sample
Towards Competitive Search Relevance For Inference-Free Learned Sparse Retrievers
https://github.com/zhiyuns/REHRSeg
https://github.com/zhongmicai/Methylation_notes
https://github.com/zhongzisha/object_detection
https://github.com/zhouhing/Mself_mmdetection
https://github.com/zhuang-group/lit
https://github.com/zhyings/cbm
https://github.com/zifuwanggg/jdml
Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels
https://github.com/zihanzhaosjtu/librisqa
PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering
https://github.com/ziming-liu/ObjectDet
https://github.com/zj463261929/darknet_mAP
https://github.com/zju-vipa/KamalEngine
Hearing Lips: Improving Lip Reading by Distilling Speech Recognizers
https://github.com/zju-vipa/cmi
Contrastive Model Inversion for Data-Free Knowledge Distillation
https://github.com/zjukg/umaea
Rethinking Uncertainly Missing and Ambiguous Visual Modality in Multi-Modal Entity Alignment
https://github.com/zml72062/dr-fwl-2
https://github.com/zoj613/pyloras
A multi-schematic classifier-independent oversampling approach for imbalanced datasets
https://github.com/zqcrafts/Labserve
https://github.com/zsk66/flame
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
https://github.com/zz10001/LITS2017-main1
https://github.com/zzhuolun/IRL
https://github.com/zzq96/mmdetection
https://github.com/zzy-zhou/renet
Event-Free Moving Object Segmentation from Moving Ego Vehicle
https://github.com/zzz47zzz/pretrained-lm-for-incremental-learning
https://github.com/zzzace2000/mimic-preprocess
Multitask learning and benchmarking with clinical time series data
https://github.com/zzzweakman/cvpr24_frcsyn_admis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.