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/MindSpore-paper-code-3/code5/tree/main/retinanet_resnet152
https://github.com/MindSpore-paper-code-3/code6/tree/main/AlphaPose
AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time
https://github.com/MindSpore-paper-code-3/code6/tree/main/cct
https://github.com/MindSpore-paper-code-3/code9/tree/main/ternarybert
https://github.com/MindSpore-paper-code-3/code9/tree/main/tinybert
Simplified TinyBERT: Knowledge Distillation for Document Retrieval
https://github.com/MindSpore-scientific-2/code-10/tree/main/Patient2Vec-A-Personalized-Interpretable
Knowledge distillation: A good teacher is patient and consistent
https://github.com/MindSpore-scientific-2/code-12/tree/main/MCA
MCA-Bench: A Multimodal Benchmark for Evaluating CAPTCHA Robustness Against VLM-based Attacks
https://github.com/MindSpore-scientific-2/code-14/tree/main/graphormer
Benchmarking Graphormer on Large-Scale Molecular Modeling Datasets
https://github.com/MindSpore-scientific-2/code-4/tree/main/Patient2Vec-A-Personalized-Interpretable
Knowledge distillation: A good teacher is patient and consistent
https://github.com/MindSpore-scientific-2/code-5/tree/main/Patient2Vec-A-Personalized-Interpretable
Knowledge distillation: A good teacher is patient and consistent
https://github.com/MindSpore-scientific-2/code-7/blob/main/ms_spike_rev_reuse.py
SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike Streams
https://github.com/MindSpore-scientific-2/code-8/tree/main/SMOTE
https://github.com/MindSpore-scientific/code-10/tree/main/Patient2Vec-A-Personalized-Interpretable
Knowledge distillation: A good teacher is patient and consistent
https://github.com/MindSpore-scientific/code-11/tree/main/Patient2Vec-A-Personalized-Interpretable
https://github.com/MindSpore-scientific/code-13/tree/main/Patient2Vec-A-Personalized-Interpretable
https://github.com/MindSpore-scientific/code-13/tree/main/signSGD
signSGD with Majority Vote is Communication Efficient And Fault Tolerant
https://github.com/MindSpore-scientific/code-4/tree/main/Patient2Vec-A-Personalized-Interpretable
Knowledge distillation: A good teacher is patient and consistent
https://github.com/MindSpore-scientific/code-7/tree/main/Beit
BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers
https://github.com/MindSpore-scientific/code-8/tree/main/Patient2Vec-A-Personalized-Interpretable
Knowledge distillation: A good teacher is patient and consistent
https://github.com/Mohit-Mithra/AuthNet
AuthNet: A Deep Learning based Authentication Mechanism using Temporal Facial Feature Movements
https://github.com/MonashAI/LIT
https://github.com/Muhammad-Huzaifaa/ObjectCompose
ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing
https://github.com/MultiPath/NA-NMT
https://github.com/Munna-Manoj/Team6_FastSpeech2_TTS
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/MustaphaBounoua/minde
Beyond Normal: On the Evaluation of Mutual Information Estimators
https://github.com/NBAiLab/notram
Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach
https://github.com/NOHYC/autonomous_driving_car_project
Learning Lightweight Lane Detection CNNs by Self Attention Distillation
https://github.com/NVIDIA/retinanet-examples
https://github.com/NYU-DICE-Lab/open_clip
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/NeelayS/Knowledge-Distillation
https://github.com/NovasMax/R3Det-Refined-Single-Stage-Detector-with-Feature-Refinement-for-RO
https://github.com/OFRIN/Tensorflow_RetinaFace
https://github.com/OML-Team/open-metric-learning
Learning Transferable Visual Models From Natural Language Supervision
https://github.com/OceanPang/Libra_R-CNN
https://github.com/OlaWod/my-fastspeech2
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.