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/HDCVLab/EDFace-Celeb-1M
공식 코드EDFace-Celeb-1M: Benchmarking Face Hallucination with a Million-scale Dataset
https://github.com/HDCVLab/MC-Blur-Dataset
공식 코드https://github.com/HIT-SCIR/ltp
공식 코드N-LTP: An Open-source Neural Language Technology Platform for Chinese
https://github.com/HKBU-HPML/CovidNet3D
공식 코드https://github.com/HKUNLP/zerogen
공식 코드ZeroGen: Efficient Zero-shot Learning via Dataset Generation
https://github.com/HKUST-Aerial-Robotics/spatiotemporal_semantic_corridor
공식 코드Safe Trajectory Generation for Complex Urban Environments Using Spatio-temporal Semantic Corridor
https://github.com/HPAI-BSC/SuSy
공식 코드Present and Future Generalization of Synthetic Image Detectors
https://github.com/HannahKirk/Hatemoji
공식 코드https://github.com/Hao840/CDFKD-MFS
공식 코드CDFKD-MFS: Collaborative Data-free Knowledge Distillation via Multi-level Feature Sharing
https://github.com/HaokunChen245/DFDG
공식 코드https://github.com/HaokunChen245/FedDAT
공식 코드FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated Learning
https://github.com/HarlinLee/brillsson
공식 코드Distilled Non-Semantic Speech Embeddings with Binary Neural Networks for Low-Resource Devices
https://github.com/HarrieO/OnlineLearningToRank
공식 코드https://github.com/HenryPengZou/ImplicitAVE
공식 코드https://github.com/HewlettPackard/separable-operator-networks
공식 코드https://github.com/HewlettPackard/trust-ml
공식 코드Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness
https://github.com/HikariTJU/LD
공식 코드https://github.com/Hoangpham13579/end_to_end_anomaly_detection
공식 코드Benchmarking Jetson Edge Devices with an End-to-end Video-based Anomaly Detection System
https://github.com/HobbitLong/RepDistiller
공식 코드https://github.com/Hyh200/Hyh200.github.io
공식 코드https://github.com/Hzzone/AgeFlow
공식 코드AgeFlow: Conditional Age Progression and Regression with Normalizing Flows
https://github.com/I2RDL2/ASTAR-3D
공식 코드A*3D Dataset: Towards Autonomous Driving in Challenging Environments
https://github.com/IAAR-Shanghai/UHGEval
공식 코드https://github.com/IBM-HRL-MLHLS/IBM-Causal-Inference-Benchmarking-Framework
공식 코드Benchmarking Framework for Performance-Evaluation of Causal Inference Analysis
https://github.com/IBM-HRL-MLHLS/IBM-Causality-Benchmarking-Framework
공식 코드Benchmarking Framework for Performance-Evaluation of Causal Inference Analysis
https://github.com/IBM/AIF360
공식 코드https://github.com/IBM/IPC-graph-data
공식 코드IPC: A Benchmark Data Set for Learning with Graph-Structured Data
https://github.com/IBM/LLM-performance-prediction
공식 코드LLM-Pilot: Characterize and Optimize Performance of your LLM Inference Services
https://github.com/IBM/document2slides
공식 코드D2S: Document-to-Slide Generation Via Query-Based Text Summarization
https://github.com/IBM/helm-enterprise-benchmark
공식 코드https://github.com/IBM/itbench-sample-scenarios
공식 코드ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks
https://github.com/IBM/itbench-sre-agent
공식 코드ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks
https://github.com/IBM/terratorch
공식 코드https://github.com/ICLab4DL/GNNBenchEffectiveness
공식 코드Rethinking the Effectiveness of Graph Classification Datasets in Benchmarks for Assessing GNNs
https://github.com/IDEA-Research/detrex
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.