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/yiren-jian/embedding-learning-fsl
Self-supervised Knowledge Distillation for Few-shot Learning
https://github.com/yiskw713/ClassActivationMapping
Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
https://github.com/yiskw713/SmoothGradCAMplusplus
Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
https://github.com/yiskw713/scorecam
Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
https://github.com/yizhongw/tk-instruct
Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks
https://github.com/ylqi/count-anything
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/ylwhxht/SRKD-DRET
Sunshine to Rainstorm: Cross-Weather Knowledge Distillation for Robust 3D Object Detection
https://github.com/yolo0226/mmdetection-master
https://github.com/yongbowin/MSMARCO-Question-Answering_annotation
MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
https://github.com/yongbowin/OpenKP_annotation
MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
https://github.com/yoonkim/neural-qcfg
StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer
https://github.com/yorkerlin/remove-the-square-root
https://github.com/yoshifumi-nakano/visual-text-to-speech
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/yossilevii100/critical_points2
Benchmarking and Analyzing Point Cloud Classification under Corruptions
https://github.com/yossilevii100/refocusing
Benchmarking and Analyzing Point Cloud Classification under Corruptions
https://github.com/youngwanLEE/rc-mae
Benchmarking Detection Transfer Learning with Vision Transformers
https://github.com/yshuqiao/cascade_rcnn_fabricDetection
https://github.com/yuchen814/codehalu
https://github.com/yudie433/darknet
https://github.com/yueatsprograms/ttt_cifar_release
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
https://github.com/yueatsprograms/ttt_imagenet_release
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
https://github.com/yufanchen96/RoDLA
RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
https://github.com/yuhangT/tf_bert
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/yukexing/3dgs-ieval-15k
LMM4LMM: Benchmarking and Evaluating Large-multimodal Image Generation with LMMs
https://github.com/yuliani29/yolotraining
https://github.com/yunqing-me/attackvlm
Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
https://github.com/yurangja99/Pytorch-Sketch-RNN
https://github.com/yuuun/clip_pytorch
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/yuyouyu32/beyonddialogue
RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models
https://github.com/yvanyin/goalflow
Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation
https://github.com/ywjawmw/shennong-tcm-evaluation-benchmark
https://github.com/yytang2012/darknet
https://github.com/yzhao062/yzhao062
https://github.com/zahrag/BIOSCAN-5M
An Empirical Study into Clustering of Unseen Datasets with Self-Supervised Encoders
https://github.com/zamnius/uNet-seg-decathlon
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.