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/paranioar/gssf
공식 코드GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric Learning
https://github.com/parham-ap/cytology_dataset
공식 코드https://github.com/passalis/pkth
공식 코드Heterogeneous Knowledge Distillation using Information Flow Modeling
https://github.com/patientzero/timage-icann2019
공식 코드https://github.com/patilli/vqa_benchmarking
공식 코드Beyond Accuracy: A Consolidated Tool for Visual Question Answering Benchmarking
https://github.com/patricia-pereira/deep-emotion-recognition-in-textual-conversations
공식 코드https://github.com/patriziobellan86/petsotaandchallenges
공식 코드https://github.com/patriziobellan86/processextractionfromtextsotaandchallenges
공식 코드https://github.com/pawpuk/curvbim
공식 코드Investigating the Impact of Hard Samples on Accuracy Reveals In-class Data Imbalance
https://github.com/pbelcak/fastbert
공식 코드https://github.com/pbelcak/perkit
공식 코드https://github.com/pbonazzi/eva
공식 코드RGB-Event Fusion with Self-Attention for Collision Prediction
https://github.com/pc2752/sep_content
공식 코드Content Based Singing Voice Extraction From a Musical Mixture
https://github.com/pcasolab/vdst-net
공식 코드https://github.com/pchlenski/hyperdt
공식 코드https://github.com/peernagy/lob_bench
공식 코드LOB-Bench: Benchmarking Generative AI for Finance -- an Application to Limit Order Book Data
https://github.com/pencilzhang/MAC-light-field-saliency-net
공식 코드Light Field Saliency Detection with Deep Convolutional Networks
https://github.com/penfever/sos-bench
공식 코드Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking
https://github.com/penghui-yang/l2d
공식 코드https://github.com/pengr/ikd-mmt
공식 코드Distill the Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine Translation
https://github.com/pengzhiliang/g2sd
공식 코드https://github.com/perib/automl_digen_benchmark
공식 코드Benchmarking AutoML algorithms on a collection of synthetic classification problems
https://github.com/peterwestai2/symbolic-knowledge-distillation
공식 코드Symbolic Knowledge Distillation: from General Language Models to Commonsense Models
https://github.com/petrichor625/hltp
공식 코드A Cognitive-Based Trajectory Prediction Approach for Autonomous Driving
https://github.com/pfnet-research/piekd
공식 코드Periodic Intra-Ensemble Knowledge Distillation for Reinforcement Learning
https://github.com/phandangthoai/Comparison-Performance-of-Spectrogram-and-Scalogram-as-Input-of-Acoustic-Recognition-Task
공식 코드Comparison Performance of Spectrogram and Scalogram as Input of Acoustic Recognition Task
https://github.com/phenixace/tomg-bench
공식 코드TOMG-Bench: Evaluating LLMs on Text-based Open Molecule Generation
https://github.com/phenomicai/bascvi
공식 코드Benchmarking and optimizing organism wide single-cell RNA alignment methods
https://github.com/phoenixz810/risebench
공식 코드Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing
https://github.com/phonchi/Cryo-RAlib
공식 코드Cryo-RALib -- a modular library for accelerating alignment in cryo-EM
https://github.com/piacuk/distillistic
공식 코드Teacher Network Calibration Improves Cross-Quality Knowledge Distillation
https://github.com/pic4ser/agriseg
공식 코드Domain Generalization for Crop Segmentation with Standardized Ensemble Knowledge Distillation
https://github.com/pic4ser/edgesrgan
공식 코드Generative Adversarial Super-Resolution at the Edge with Knowledge Distillation
https://github.com/pic4ser/pic4rl_gym
공식 코드https://github.com/pic4ser/unsupervised-novelty-detection-methods-benchmarking-with-wavelet-decomposition
공식 코드Unsupervised Novelty Detection Methods Benchmarking with Wavelet Decomposition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.