https://github.com/glory20h/FitHuBERT
공식 코드FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised Learning
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/gmberton/deep-visual-geo-localization-benchmark
공식 코드https://github.com/gmc-drl/apdmmo
공식 코드Accurate Peak Detection in Multimodal Optimization via Approximated Landscape Learning
https://github.com/gmkim-ai/promptkd
공식 코드PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning
https://github.com/gmlwns2000/sea-attention
공식 코드https://github.com/gofigure-lanl/figure-segmentation
공식 코드DeepPatent2: A Large-Scale Benchmarking Corpus for Technical Drawing Understanding
https://github.com/goldblum/AdversariallyRobustDistillation
공식 코드https://github.com/google-deepmind/neptune
공식 코드Neptune: The Long Orbit to Benchmarking Long Video Understanding
https://github.com/google-research-datasets/2.5vrd
공식 코드https://github.com/google-research-datasets/Textual-Entailment-New-Protocols
공식 코드New Protocols and Negative Results for Textual Entailment Data Collection
https://github.com/google-research-datasets/bim
공식 코드Benchmarking Attribution Methods with Relative Feature Importance
https://github.com/google-research-datasets/egotempo
공식 코드Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos
https://github.com/google-research-datasets/screen_qa
공식 코드ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots
https://github.com/google-research/android_world
공식 코드AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents
https://github.com/google-research/bert
공식 코드Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
https://github.com/google-research/big_vision
공식 코드Knowledge distillation: A good teacher is patient and consistent
https://github.com/google-research/deep_ope
공식 코드https://github.com/google-research/federated
공식 코드Motley: Benchmarking Heterogeneity and Personalization in Federated Learning
https://github.com/google-research/federated/tree/master/personalization_benchmark
공식 코드Motley: Benchmarking Heterogeneity and Personalization in Federated Learning
https://github.com/google-research/google-research
공식 코드Class-Balanced Distillation for Long-Tailed Visual Recognition
https://github.com/google-research/google-research/tree/master/bam
공식 코드BAM! Born-Again Multi-Task Networks for Natural Language Understanding
https://github.com/google-research/google-research/tree/master/class_balanced_distillation
공식 코드Class-Balanced Distillation for Long-Tailed Visual Recognition
https://github.com/google-research/google-research/tree/master/compositional_rl
공식 코드Adversarial Environment Generation for Learning to Navigate the Web
https://github.com/google-research/google-research/tree/master/fvlm
공식 코드F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models
https://github.com/google-research/google-research/tree/master/quantum_sample_learning
공식 코드https://github.com/google-research/google-research/tree/master/scann
공식 코드Accelerating Large-Scale Inference with Anisotropic Vector Quantization
https://github.com/google-research/graphworld
공식 코드https://github.com/google-research/long-range-arena
공식 코드https://github.com/google-research/mnist-c
공식 코드https://github.com/google-research/nasbench
공식 코드NAS-Bench-101: Towards Reproducible Neural Architecture Search
https://github.com/google-research/population-dynamics
공식 코드General Geospatial Inference with a Population Dynamics Foundation Model
https://github.com/google-research/robopianist
공식 코드RoboPianist: Dexterous Piano Playing with Deep Reinforcement Learning
https://github.com/google/deluca
공식 코드Deluca -- A Differentiable Control Library: Environments, Methods, and Benchmarking
https://github.com/google/haloquest
공식 코드HaloQuest: A Visual Hallucination Dataset for Advancing Multimodal Reasoning
https://github.com/gorilla-lab-scut/bico-net
공식 코드BiCo-Net: Regress Globally, Match Locally for Robust 6D Pose Estimation
https://github.com/gorilla-lab-scut/dcl-net
공식 코드DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.