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/eynaij/mmdetection_he
https://github.com/fabianwinter93/JAX/tree/main/FastFeedForwardNetwork
https://github.com/fabiofumarola/ultrayolo
https://github.com/facebookresearch/EgoTV
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
https://github.com/facebookresearch/augmentation-corruption
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
https://github.com/facebookresearch/brainmagick
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/facebookresearch/clip-rocket
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/facebookresearch/detectron2
https://github.com/facebookresearch/disentangling-correlated-factors
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
https://github.com/facebookresearch/habitat-api
https://github.com/facebookresearch/habitat-challenge
https://github.com/facebookresearch/habitat-lab
https://github.com/facebookresearch/meta_secalign
InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents
https://github.com/facebookresearch/metaicl
Multitask Prompted Training Enables Zero-Shot Task Generalization
https://github.com/facebookresearch/multimodal_rewardbench
SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension
https://github.com/facebookresearch/soundspaces-challenge
https://github.com/facebookresearch/ssl-relation-prediction
https://github.com/facebookresearch/stopes
https://github.com/facebookresearch/vissl
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/facebookresearch/wav2letter
https://github.com/fangyi-chen/sqr
https://github.com/fanq15/GCoNet
https://github.com/fanzhichen/ncd-iic
Class-relation Knowledge Distillation for Novel Class Discovery
https://github.com/farbodtaymouri/BERT-GAN
An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction
https://github.com/fastscience-ai/medflamingo
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/fcUalberta/UAlberta-Multimedia-Masters-Program-Interpretable-AI-Part_1_2
Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
https://github.com/fchollet/arc-agi
https://github.com/feedbackward/addro
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
https://github.com/fehmikahraman/mmdetection
https://github.com/feidfoe/AdjustBnd4Imbalance
https://github.com/feinanshan/TDNet
Temporally Distributed Networks for Fast Video Semantic Segmentation
https://github.com/felixdenbreejen/tabforestpfn
Why do tree-based models still outperform deep learning on tabular data?
https://github.com/feng-lab/mmdetection
https://github.com/fiabdu/Commonly-Interesting-Images
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/filipbasara0/simple-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.