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/helme/ecg_ptbxl_benchmarking
공식 코드Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL
https://github.com/helmholtz-ai-energy/oialr
공식 코드https://github.com/hendrycks/robustness
공식 코드Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
https://github.com/henggao12/oal
공식 코드https://github.com/hewlettpackard/dc-rl
공식 코드https://github.com/hexiaoxiao-cs/fedml-knee
공식 코드https://github.com/hexuandeng/mono4simt
공식 코드Improving Simultaneous Machine Translation with Monolingual Data
https://github.com/hexuandeng/newterm
공식 코드NewTerm: Benchmarking Real-Time New Terms for Large Language Models with Annual Updates
https://github.com/hfut-mialab/slidegcd
공식 코드https://github.com/hfutami/distill-bert-for-seq2seq-asr
공식 코드Distilling the Knowledge of BERT for Sequence-to-Sequence ASR
https://github.com/hfutqian/SwitOKD
공식 코드https://github.com/hguimaraes/robustdistiller
공식 코드An Efficient End-to-End Approach to Noise Invariant Speech Features via Multi-Task Learning
https://github.com/hhi-aml/histobenchmark
공식 코드https://github.com/hhw-zhou/tsmmg
공식 코드Instruction Multi-Constraint Molecular Generation Using a Teacher-Student Large Language Model
https://github.com/hi-archers/mlake
공식 코드MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models
https://github.com/hi-ft/erd
공식 코드Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation
https://github.com/hicai-zju/sciknoweval
공식 코드SciKnowEval: Evaluating Multi-level Scientific Knowledge of Large Language Models
https://github.com/hiest/distmis
공식 코드Distributing Deep Learning Hyperparameter Tuning for 3D Medical Image Segmentation
https://github.com/hikari-NYU/Emoji_Prediction_Datasets_MMS
공식 코드https://github.com/hikopensource/davar-lab-ocr
공식 코드Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting
https://github.com/hikvision-research/davar-lab-ml
공식 코드https://github.com/hilab-git/cdma
공식 코드Semi-supervised Pathological Image Segmentation via Cross Distillation of Multiple Attentions
https://github.com/hilab-git/pa-seg
공식 코드https://github.com/hisaolabsustc/benchss
공식 코드https://github.com/hit-sirs/crobim
공식 코드Cross-Modal Bidirectional Interaction Model for Referring Remote Sensing Image Segmentation
https://github.com/hito2448/CRD
공식 코드Multimodal Industrial Anomaly Detection by Crossmodal Reverse Distillation
https://github.com/hito2448/urd
공식 코드Unlocking the Potential of Reverse Distillation for Anomaly Detection
https://github.com/hitum-dev/pollmgraph
공식 코드PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics
https://github.com/hiyouga/llama-factory
공식 코드https://github.com/hiyuchang/leadq
공식 코드Learn How to Query from Unlabeled Data Streams in Federated Learning
https://github.com/hj-n/labeled-datasets
공식 코드Sanity Check for External Clustering Validation Benchmarks using Internal Validation Measures
https://github.com/hjdw2/Exit-Ensemble-Distillation
공식 코드Students are the Best Teacher: Exit-Ensemble Distillation with Multi-Exits
https://github.com/hjdw2/sembg
공식 코드Low-Cost Self-Ensembles Based on Multi-Branch Transformation and Grouped Convolution
https://github.com/hjytsuki/mldebugging
공식 코드MLDebugging: Towards Benchmarking Code Debugging Across Multi-Library Scenarios
https://github.com/hku-system-security-lab/congra
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.