https://github.com/snoop2head/Deep-Encoder-Shallow-Decoder
Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translation
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/soccergame/darknet
https://github.com/softsys4ai/neural-distiller
Ensemble Knowledge Distillation for Learning Improved and Efficient Networks
https://github.com/solapark/da_yolo
https://github.com/solapark/darknet_interpark
https://github.com/solapark/darknet_partdet
https://github.com/solapark/darknet_partdet_tmp
https://github.com/somiltg/bert
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/sotif-avlab/pesotif
https://github.com/srihari-humbarwadi/retinanet-tensorflow2.x
https://github.com/srihari-humbarwadi/tensorflow_retinanet
https://github.com/sriloksagar/fashion-mnist
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
https://github.com/sseung0703/IEPKT
https://github.com/sseung0703/KD_methods_with_TF
Graph-based Knowledge Distillation by Multi-head Attention Network
https://github.com/sswetank-CS/MIL
Multiple Instance Learning: A Survey of Problem Characteristics and Applications
https://github.com/stanfordvl/atp-video-language
https://github.com/starry-sky6688/marl-algorithms
https://github.com/stdereka/knowledge-distillation
https://github.com/stefan-it/europeana-bert
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
https://github.com/stevenboys/moon
OpenOOD: Benchmarking Generalized Out-of-Distribution Detection
https://github.com/stevenzhou2017/darknet_AlexeyAB
https://github.com/stovecat/convcodeworld
BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions
https://github.com/sudharavali/objectDetectionYOLO
https://github.com/suilin0432/mmdetectionWithCodeAnnotations
https://github.com/suinleelab/path_explain
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
https://github.com/sulasen/race-events-recognition-1
https://github.com/sumilergao/sungen
ZeroGen: Efficient Zero-shot Learning via Dataset Generation
https://github.com/sungnyun/LG-knowledge-distillation
https://github.com/sunwei925/uiqa
https://github.com/super5-22/habitat-vis
https://github.com/sushovanjena/Attention-aware-Entropy-Distillation-for-Anomaly-Detection
Attend, Distill, Detect: Attention-aware Entropy Distillation for Anomaly Detection
https://github.com/swarooprm/DQI
https://github.com/swasun/VQ-VAE-images
https://github.com/symbioticlab/zeus
The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization
https://github.com/syscv/ovtrack
https://github.com/szbonaldo/fedmlp
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.