https://github.com/mdabbah/COOD_benchmarking
공식 코드A framework for benchmarking class-out-of-distribution detection and its application to ImageNet
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/mdswyz/dmd
공식 코드https://github.com/medaitech/scrd4ad
공식 코드Scale-Aware Contrastive Reverse Distillation for Unsupervised Medical Anomaly Detection
https://github.com/meghdadk/DDUp
공식 코드Detect, Distill and Update: Learned DB Systems Facing Out of Distribution Data
https://github.com/megvii-research/ICD
공식 코드Instance-Conditional Knowledge Distillation for Object Detection
https://github.com/megvii-research/cvpr2023-unidistill
공식 코드https://github.com/megvii-research/kd-mvs
공식 코드KD-MVS: Knowledge Distillation Based Self-supervised Learning for Multi-view Stereo
https://github.com/megvii-research/mdistiller
공식 코드https://github.com/megvii-research/occdepth
공식 코드OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion
https://github.com/mehmetaygun/4d-pls
공식 코드https://github.com/mehrzadshm/built-bench-paper
공식 코드Benchmarking pre-trained text embedding models in aligning built asset information
https://github.com/melanibe/failure_detection_benchmark
공식 코드Failure Detection in Medical Image Classification: A Reality Check and Benchmarking Testbed
https://github.com/melqkiades/deep-wetlands
공식 코드https://github.com/mengfeidu/embspatial-bench
공식 코드https://github.com/mengqidyangge/hierkd
공식 코드Open-Vocabulary One-Stage Detection with Hierarchical Visual-Language Knowledge Distillation
https://github.com/menik1126/TRIGO
공식 코드TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models
https://github.com/mertan-a/towards-multi-morphology-controllers
공식 코드Towards Multi-Morphology Controllers with Diversity and Knowledge Distillation
https://github.com/meta-knowledge-lab/dlb
공식 코드Self-Distillation from the Last Mini-Batch for Consistency Regularization
https://github.com/metaagentx/opencaptchaworld
공식 코드https://github.com/metacopilot/dseval
공식 코드https://github.com/metadriverse/metadrive
공식 코드MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning
https://github.com/metaevo/q-mamba
공식 코드Meta-Black-Box-Optimization through Offline Q-function Learning
https://github.com/metaslam/alto
공식 코드ALTO: A Large-Scale Dataset for UAV Visual Place Recognition and Localization
https://github.com/mever-team/distill-and-select
공식 코드DnS: Distill-and-Select for Efficient and Accurate Video Indexing and Retrieval
https://github.com/mever-team/sidbench
공식 코드SIDBench: A Python Framework for Reliably Assessing Synthetic Image Detection Methods
https://github.com/mgaido91/FBK-fairseq-ST
공식 코드https://github.com/mgbukov/rl_disentangle
공식 코드Reinforcement Learning to Disentangle Multiqubit Quantum States from Partial Observations
https://github.com/mgwillia/unsupervised-analysis
공식 코드https://github.com/mi2datalab/agg2exp
공식 코드Aggregated Attributions for Explanatory Analysis of 3D Segmentation Models
https://github.com/miaoxiong2320/llm-uncertainty
공식 코드Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
https://github.com/mic-dkfz/foundation-models-for-cbmir
공식 코드Leveraging Foundation Models for Content-Based Medical Image Retrieval in Radiology
https://github.com/mic-dkfz/napari-nninteractive
공식 코드https://github.com/mic-dkfz/nninteractive
공식 코드https://github.com/mic-dkfz/nnssl
공식 코드https://github.com/miccaiif/weno
공식 코드Bi-directional Weakly Supervised Knowledge Distillation for Whole Slide Image Classification
https://github.com/miccunifi/circo
공식 코드iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.