https://github.com/bmucsanyi/bud
공식 코드Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
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/bmucsanyi/untangle
공식 코드Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
https://github.com/bnn-upc/graphlaxy
공식 코드Bias Reduction via Cooperative Bargaining in Synthetic Graph Dataset Generation
https://github.com/boa2004plaust/vimd
공식 코드Vision Mamba Distillation for Low-resolution Fine-grained Image Classification
https://github.com/bobwan1995/zeroshot-hoi-with-clip
공식 코드Exploiting CLIP for Zero-shot HOI Detection Requires Knowledge Distillation at Multiple Levels
https://github.com/bobxwu/antileak-bench
공식 코드https://github.com/boevalab/scssl-bench
공식 코드scSSL-Bench: Benchmarking Self-Supervised Learning for Single-Cell Data
https://github.com/boleima/topro
공식 코드ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks
https://github.com/booml247/ctlsan
공식 코드https://github.com/boschresearch/causalassembly
공식 코드$\texttt{causalAssembly}$: Generating Realistic Production Data for Benchmarking Causal Discovery
https://github.com/boschresearch/mlfuzz
공식 코드https://github.com/boschresearch/neuzzplusplus
공식 코드https://github.com/bowang-lab/bleep
공식 코드https://github.com/bowang-lab/medsam
공식 코드Segment Anything in Medical Images and Videos: Benchmark and Deployment
https://github.com/bowen-upenn/personamem
공식 코드https://github.com/bowenl0218/mmvc_video_codec
공식 코드https://github.com/braindatalab/gecobench
공식 코드GECOBench: A Gender-Controlled Text Dataset and Benchmark for Quantifying Biases in Explanations
https://github.com/brandonhanx/textreid
공식 코드https://github.com/braqiiit/qrealboost
공식 코드https://github.com/brave-experiments/melt-public
공식 코드https://github.com/brentp/bwa-meth
공식 코드https://github.com/brianchi0607/PREFALLKD-PRE-IMPACT-FALL-DETECTION-VIA-CNN-VIT-KNOWLEDGE-DISTILLATION
공식 코드PreFallKD: Pre-Impact Fall Detection via CNN-ViT Knowledge Distillation
https://github.com/brianxiang123/eegetcovariatedistributionalshift
공식 코드https://github.com/brilliantcheng/slkd
공식 코드Improving Knowledge Distillation via Transferring Learning Ability
https://github.com/brjathu/RPSnet
공식 코드An Adaptive Random Path Selection Approach for Incremental Learning
https://github.com/brjathu/SKD
공식 코드Self-supervised Knowledge Distillation for Few-shot Learning
https://github.com/brucelyu17/sc-tc-bench
공식 코드Characterizing Bias: Benchmarking Large Language Models in Simplified versus Traditional Chinese
https://github.com/brucewsy/ad-kd
공식 코드AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression
https://github.com/bryanlimy/ViV1T
공식 코드https://github.com/buds-lab/aldiplusplus
공식 코드ALDI++: Automatic and parameter-less discord and outlier detection for building energy load profiles
https://github.com/buds-lab/energystar-plus-plus
공식 코드EnergyStar++: Towards more accurate and explanatory building energy benchmarking
https://github.com/bupt-reasoning-lab/financereasoning
공식 코드https://github.com/burchim/iqa-conformer-bns
공식 코드Conformer and Blind Noisy Students for Improved Image Quality Assessment
https://github.com/butspeechfit/diarizen
공식 코드Efficient and Generalizable Speaker Diarization via Structured Pruning of Self-Supervised Models
https://github.com/by-liu/confkd
공식 코드Segmentation with mixed supervision: Confidence maximization helps knowledge distillation
https://github.com/bytedance-seed/bm-code
공식 코드ByteMorph: Benchmarking Instruction-Guided Image Editing with Non-Rigid Motions
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.