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/MS-P3/code7/tree/main/van
VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs
https://github.com/MahmoudWahdan/dialog-nlu
On the Effect of Dropping Layers of Pre-trained Transformer Models
https://github.com/MalvinaNikandrou/contvqa
RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning
https://github.com/MariefW/6.-trainingYOLO
https://github.com/Marior87/Telegram_Bot
https://github.com/MarkHershey/arxiv-dl
https://github.com/MartinPawel/ProbabilisticallyRobustRecourse
CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
https://github.com/MasLiang/Learning-without-Forgetting-using-Pytorch
https://github.com/Maskify/darknet
https://github.com/MateusMaiaDS/rmachines
Random Machines: A bagged-weighted support vector model with free kernel choice
https://github.com/MatthewAbugeja/osnet
Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch
https://github.com/MatusPilnan/nsiete-project
https://github.com/Maz101/Bert
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/Maz101/pretrainingdataset
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/MegEngine/Models/tree/master/official/vision/detection
https://github.com/Merenguelkl/Reverse_Disstilation
Anomaly Detection via Reverse Distillation from One-Class Embedding
https://github.com/Milan-Chicago/GLG-Automated-Meta-data-Tagging
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
https://github.com/MinJunKang/CIFAR-100--Knowledge-Distillation-with-Augmented-Data
https://github.com/MinJunKang/ImageNet-Knowledge-Distillation
https://github.com/MinJunKang/Knowledge-Distillation_MNIST
https://github.com/Mind23-2/MindCode-149
Simplified TinyBERT: Knowledge Distillation for Document Retrieval
https://github.com/Mind23-2/MindCode-172
Pool of Experts: Realtime Querying Specialized Knowledge in Massive Neural Networks
https://github.com/Mind23-2/MindCode-176
https://github.com/MindCode-4/code-12/tree/main/Learning-with-Noisy-Labels
Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations
https://github.com/MindCode-4/code-13/tree/main/sa-mlp-distilling-graph
SA-MLP: Distilling Graph Knowledge from GNNs into Structure-Aware MLP
https://github.com/MindCode-4/code-3/tree/main/dbrx
https://github.com/MindCode-4/code-3/tree/main/distilbert
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
https://github.com/MindCode-4/code-3/tree/main/falcon
FALCON: Feature-Label Constrained Graph Net Collapse for Memory Efficient GNNs
https://github.com/MindCode-4/code-5/tree/main/tinybert
TinyBERT: Distilling BERT for Natural Language Understanding
https://github.com/MindCode-4/code-8/tree/main/sa-mlp-distilling-graph
SA-MLP: Distilling Graph Knowledge from GNNs into Structure-Aware MLP
https://github.com/MindCode-4/code-9/tree/main/sa-mlp-distilling-graph
SA-MLP: Distilling Graph Knowledge from GNNs into Structure-Aware MLP
https://github.com/MindSpore-paper-code-2/code2/tree/main/RefineNet
Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations
https://github.com/MindSpore-paper-code-2/code3/tree/main/TinySAM
TinySAM: Pushing the Envelope for Efficient Segment Anything Model
https://github.com/MindSpore-paper-code-2/code3/tree/main/yolov3_resnet18
Benchmarking YOLOv5 and YOLOv7 models with DeepSORT for droplet tracking applications
https://github.com/MindSpore-paper-code-2/code399/tree/main/Bert
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.