https://github.com/cvblab/kd_resolution
공식 코드Attention to detail: inter-resolution knowledge distillation
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/cvblab/mitosis-uts
공식 코드Attention to detail: inter-resolution knowledge distillation
https://github.com/cvi-szu/facebench
공식 코드https://github.com/cvi-yangwn/benchmark-gnn-for-multivariate-time-series-classification
공식 코드https://github.com/cvjena/deic
공식 코드Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification
https://github.com/cvmi-lab/kdep
공식 코드https://github.com/cvmi-lab/reskd
공식 코드Rethinking Resolution in the Context of Efficient Video Recognition
https://github.com/cvmi-lab/sparsekd
공식 코드Towards Efficient 3D Object Detection with Knowledge Distillation
https://github.com/cwcleghornai/cornn
공식 코드A Continuous Optimisation Benchmark Suite from Neural Network Regression
https://github.com/cxh-research/guidedhybsensuir
공식 코드https://github.com/cycl2018/recommendation-editing
공식 코드Better Late Than Never: Formulating and Benchmarking Recommendation Editing
https://github.com/cyrilvallez/image-manipulation-detection
공식 코드Needle In A Haystack, Fast: Benchmarking Image Perceptual Similarity Metrics At Scale
https://github.com/cysecbench/dataset
공식 코드https://github.com/czjghost/afs
공식 코드New Insights on Relieving Task-Recency Bias for Online Class Incremental Learning
https://github.com/d-li14/SAN
공식 코드Learning to Learn Parameterized Classification Networks for Scalable Input Images
https://github.com/da-wen-er/vdss
공식 코드A Benchmarking Dataset with 2440 Organic Molecules for Volume Distribution at Steady State
https://github.com/da03/implicit_chain_of_thought
공식 코드Implicit Chain of Thought Reasoning via Knowledge Distillation
https://github.com/dadecampo/SafeRLAUV
공식 코드Aquatic Navigation: A Challenging Benchmark for Deep Reinforcement Learning
https://github.com/daiweiworking/RobustDeepLearningUsingPerturbations
공식 코드Benchmarking Robustness of Deep Learning Classifiers Using Two-Factor Perturbation
https://github.com/daixinghome/Distill_GID_detectron2
공식 코드https://github.com/dalision/modalbiasavsr
공식 코드https://github.com/damo-nlp-sg/tempreason
공식 코드Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models
https://github.com/daniel-gong/chatgpt-wm
공식 코드https://github.com/danielemalitesta/rel-deeplearning-recsys
공식 코드https://github.com/dashends/codesyntax
공식 코드https://github.com/datamllab/Mitigating_Gender_Bias_In_Captioning_System
공식 코드https://github.com/dataparameters/Ternary-Embedding-Models
공식 코드Efficient Ternary Weight Embedding Model: Bridging Scalability and Performance
https://github.com/datascienceuibk/arabicaqa
공식 코드ArabicaQA: A Comprehensive Dataset for Arabic Question Answering
https://github.com/datasec-lab/certifiedattack
공식 코드https://github.com/davidenapolitano/bones
공식 코드https://github.com/davidrburt/pm25-forecasting-framework
공식 코드A Framework for Evaluating PM2.5 Forecasts from the Perspective of Individual Decision Making
https://github.com/davisrbr/bsd-misuse
공식 코드https://github.com/dbmdz/berts
공식 코드https://github.com/dd-duda/bitdistiller
공식 코드BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation
https://github.com/dddavid4real/BLEND
공식 코드BLEND: Behavior-guided Neural Population Dynamics Modeling via Privileged Knowledge Distillation
https://github.com/ddidacus/mol-moe
공식 코드Mol-MoE: Training Preference-Guided Routers for Molecule Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.