Papers with Code 아카이브

Self-Knowledge Distillation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 0
보존된 평가 기록: 0

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/Kennethborup/self_distillation

공식 코드

Even your Teacher Needs Guidance: Ground-Truth Targets Dampen Regularization Imposed by Self-Distillation

https://github.com/Lee-Gihun/FedNTD

공식 코드

Preservation of the Global Knowledge by Not-True Distillation in Federated Learning

https://github.com/Lee-Gihun/FedSOL

공식 코드

FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning

https://github.com/MingiJi/FRSKD

공식 코드

Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation

https://github.com/ThomasWestfechtel/SWG

공식 코드

Combining inherent knowledge of vision-language models with unsupervised domain adaptation through strong-weak guidance

https://github.com/XinshaoAmosWang/ProSelfLC-CVPR2021

공식 코드

ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks

https://github.com/aieson/crossmatch

공식 코드

CrossMatch: Enhance Semi-Supervised Medical Image Segmentation with Perturbation Strategies and Knowledge Distillation

https://github.com/alinlab/cs-kd

공식 코드

Regularizing Class-wise Predictions via Self-knowledge Distillation

https://github.com/amink8/folk

공식 코드

Frequency-Guided Masking for Enhanced Vision Self-Supervised Learning

https://github.com/ccasimiro88/self-distillation-gxlt-qa

공식 코드

Promoting Generalized Cross-lingual Question Answering in Few-resource Scenarios via Self-knowledge Distillation

https://github.com/chakkritte/SalNAS

공식 코드

SalNAS: Efficient Saliency-prediction Neural Architecture Search with self-knowledge distillation

https://github.com/cseeyangchen/c2vl

공식 코드

Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation Learning

https://github.com/flagopen/flagembedding

공식 코드

BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation

https://github.com/grispeut/udfa

공식 코드

Robust and Accurate Object Detection via Self-Knowledge Distillation

https://github.com/guanghaozhu663/skd-tstsan

공식 코드

Three-Stream Temporal-Shift Attention Network Based on Self-Knowledge Distillation for Micro-Expression Recognition

https://github.com/guojiaqi-1020/medivlad

공식 코드

Efficient Lung Ultrasound Severity Scoring Using Dedicated Feature Extractor

https://github.com/idea-research/dwpose

공식 코드

Effective Whole-body Pose Estimation with Two-stages Distillation

https://github.com/juyongjiang/barec

공식 코드

Improving Sequential Recommendations via Bidirectional Temporal Data Augmentation with Pre-training

https://github.com/lgcnsai/ps-kd-pytorch

공식 코드

Self-Knowledge Distillation with Progressive Refinement of Targets

https://github.com/liujing1023/graph-based-knowledge-distillation

공식 코드

Graph-based Knowledge Distillation: A survey and experimental evaluation

https://github.com/maxiaum/kdia

공식 코드

Tackling Data Heterogeneity in Federated Learning through Knowledge Distillation with Inequitable Aggregation

https://github.com/nlpyang/NoisySumm

공식 코드

Noisy Self-Knowledge Distillation for Text Summarization

https://github.com/regan-zhang/hadis

공식 코드

Deep Clustering with Diffused Sampling and Hardness-aware Self-distillation

https://github.com/sapienzanlp/leakdistill

공식 코드

Incorporating Graph Information in Transformer-based AMR Parsing

https://github.com/sungwon-han/dualfair

공식 코드

DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervision

https://github.com/uark-aicv/ecg_ssl_12lead

공식 코드

Multimodality Multi-Lead ECG Arrhythmia Classification using Self-Supervised Learning

https://github.com/usail-hkust/rdat

공식 코드

Robust Spatiotemporal Traffic Forecasting with Reinforced Dynamic Adversarial Training

https://github.com/winycg/self-kd-lib

공식 코드

MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition

https://github.com/xucong-parsifal/lightskd

공식 코드

Lightweight Self-Knowledge Distillation with Multi-source Information Fusion

https://github.com/yuanli2333/Teacher-free-Knowledge-Distillation

공식 코드

Revisiting Knowledge Distillation via Label Smoothing Regularization

https://github.com/yzd-v/cls_KD

공식 코드

From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.