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/irmlma/mobility-simulation-cdpm
공식 코드Synthetic location trajectory generation using categorical diffusion models
https://github.com/is2lab/s-eval
공식 코드S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models
https://github.com/isayevlab/geom-drugs-3dgen-evaluation
공식 코드GEOM-Drugs Revisited: Toward More Chemically Accurate Benchmarks for 3D Molecule Generation
https://github.com/isee-laboratory/bpf
공식 코드Bridge Past and Future: Overcoming Information Asymmetry in Incremental Object Detection
https://github.com/isee-laboratory/ppt
공식 코드Progressive Pretext Task Learning for Human Trajectory Prediction
https://github.com/ishikaalunawat/231aproj
공식 코드https://github.com/ishikura-a/aug-kd
공식 코드AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation
https://github.com/isle-dev/ecbd
공식 코드https://github.com/ismail31416/luminet
공식 코드LumiNet: The Bright Side of Perceptual Knowledge Distillation
https://github.com/istarryn/dllm2rec
공식 코드https://github.com/itemzheng/kddaug
공식 코드Rethinking Data Augmentation for Robust Visual Question Answering
https://github.com/itsnotacie/nn-fedkd-hybrid
공식 코드FedKD-hybrid: Federated Hybrid Knowledge Distillation for Lithography Hotspot Detection
https://github.com/itssmutnuri/gnnvariants
공식 코드Global Prediction of COVID-19 Variant Emergence Using Dynamics-Informed Graph Neural Networks
https://github.com/ivalab/Benchmarking_SLAM
공식 코드Characterizing SLAM Benchmarks and Methods for the Robust Perception Age
https://github.com/ivan-chai/hotpp-benchmark
공식 코드HoTPP Benchmark: Are We Good at the Long Horizon Events Forecasting?
https://github.com/iviplab/lccrf
공식 코드Leaning Compact and Representative Features for Cross-Modality Person Re-Identification
https://github.com/ivonacolakovic/synthgap-mitigation-using-kd-in-ffr
공식 코드How Knowledge Distillation Mitigates the Synthetic Gap in Fair Face Recognition
https://github.com/iwan-rg/saudi_privacy_policy
공식 코드https://github.com/iyempissy/privgnn
공식 코드Releasing Graph Neural Networks with Differential Privacy Guarantees
https://github.com/izaznov/adamz
공식 코드AdamZ: An Enhanced Optimisation Method for Neural Network Training
https://github.com/j-adamczyk/apis_tox_dataset
공식 코드ApisTox: a new benchmark dataset for the classification of small molecules toxicity on honey bees
https://github.com/j-bac/scikit-dimension
공식 코드Scikit-dimension: a Python package for intrinsic dimension estimation
https://github.com/jaabmar/kernel-test-bias
공식 코드https://github.com/jacobfulano/cyclic-learning-rate-schedules
공식 코드Fast Benchmarking of Accuracy vs. Training Time with Cyclic Learning Rates
https://github.com/jacobswan1/SEED
공식 코드SEED: Self-supervised Distillation For Visual Representation
https://github.com/jacobzhaoziyuan/ACT-Net
공식 코드https://github.com/jadie1/medseguq
공식 코드Benchmarking Scalable Epistemic Uncertainty Quantification in Organ Segmentation
https://github.com/jaewoo97/kdtf
공식 코드Multi-modal Knowledge Distillation-based Human Trajectory Forecasting
https://github.com/jahanpd/missingness
공식 코드Dealing with missing data using attention and latent space regularization
https://github.com/jakobhavtorn/benchmarking-lvms
공식 코드https://github.com/james-flemings/dp_compress
공식 코드Differentially Private Knowledge Distillation via Synthetic Text Generation
https://github.com/jamespark3922/localized-skd
공식 코드Localized Symbolic Knowledge Distillation for Visual Commonsense Models
https://github.com/jamespark3922/lskd
공식 코드Localized Symbolic Knowledge Distillation for Visual Commonsense Models
https://github.com/jameszhou-gl/gpt-4v-distribution-shift
공식 코드How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary Investigation
https://github.com/jamycheung/ISSAFE
공식 코드ISSAFE: Improving Semantic Segmentation in Accidents by Fusing Event-based Data
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.