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/V-Sense/Aesthetic-Image-Captioning-ICCVW-2019
https://github.com/VITA-Group/Large_Scale_GCN_Benchmarking
A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking
https://github.com/Vchitect/Vchitect-2.0
Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models
https://github.com/Vidhiwar/roughness-index
Roughness Index and Roughness Distance for Benchmarking Medical Segmentation
https://github.com/Vidhiwar/roughness-index-distance
Roughness Index and Roughness Distance for Benchmarking Medical Segmentation
https://github.com/ViswanathaReddyGajjala/EfficientNet-RetinaNet
https://github.com/Viveksbawa/SARAS-ESAD-Baseline
https://github.com/Walter-B/bert-20-classes
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/WangY0906/mmdetection-for-study
https://github.com/Wangxy2180/darknetKinectDetect
https://github.com/WenjieDu/SAITS
https://github.com/WenkeHuang/Pytorch_FedMD
FedMD: Heterogenous Federated Learning via Model Distillation
https://github.com/Wenyueh/LLMforRS_item_representation
https://github.com/WilliamLiPro/LpSS
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
https://github.com/WilliamPeng38/Fashion
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
https://github.com/XAI-liacs/BLADE
COCO: The Large Scale Black-Box Optimization Benchmarking (bbob-largescale) Test Suite
https://github.com/XINZXZHANG/Bert_repo
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/XanaduAI/pennylane
Better than classical? The subtle art of benchmarking quantum machine learning models
https://github.com/Xieyangxinyu/Unbiased-Watermark-via-Maximal-Coupling
WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models
https://github.com/XinshaoAmosWang/ProSelfLC
ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks
https://github.com/XinshaoAmosWang/ProSelfLC-CVPR21
ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks
https://github.com/YIZHE12/fashiontags
https://github.com/YIZHE12/robots
https://github.com/YaohuiZeng/biglasso
https://github.com/Yashgh7076/Eluvio-ML-Scene-Segmentation
https://github.com/YeLyuUT/MMDET
https://github.com/YeLyuUT/VISLNet
https://github.com/Yochengliu/MLIC-KD-WSD
Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection
https://github.com/Yonder-OSS/D3M-Primitives
https://github.com/Youmin-Kim/GLD
https://github.com/YoushaaMurhij/FasterCNN_Object_Detection
https://github.com/YuanGongND/ast
CMKD: CNN/Transformer-Based Cross-Model Knowledge Distillation for Audio Classification
https://github.com/YuanGongND/ssast
CMKD: CNN/Transformer-Based Cross-Model Knowledge Distillation for Audio Classification
https://github.com/YutingLi0606/SURE
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
https://github.com/YvanG/VQGAN-CLIP
Learning Transferable Visual Models From Natural Language Supervision
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.