Papers with Code 아카이브

Knowledge Distillation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/jpeg-aic/dataset-jpeg-ai-sdr25

공식 코드

Subjective Visual Quality Assessment for High-Fidelity Learning-Based Image Compression

https://github.com/jpfolch/catechol_solvent_selection

공식 코드

The Catechol Benchmark: Time-series Solvent Selection Data for Few-shot Machine Learning

https://github.com/jpmorganchase/llm-email-spam-detection

공식 코드

Spam-T5: Benchmarking Large Language Models for Few-Shot Email Spam Detection

https://github.com/jppbsi/LibOPT

공식 코드

LibOPT: An Open-Source Platform for Fast Prototyping Soft Optimization Techniques

https://github.com/jrnlp/multi-eup

공식 코드

Multi-EuP: The Multilingual European Parliament Dataset for Analysis of Bias in Information Retrieval

https://github.com/jsalbert/biotorch

공식 코드

Benchmarking the Accuracy and Robustness of Feedback Alignment Algorithms

https://github.com/jsandersen/cmt

공식 코드

Efficient, Uncertainty-based Moderation of Neural Networks Text Classifiers

https://github.com/jswati31/cuda-ghr

공식 코드

CUDA-GHR: Controllable Unsupervised Domain Adaptation for Gaze and Head Redirection

https://github.com/jszheng21/race

공식 코드

Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models

https://github.com/juanhui28/heart

공식 코드

Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking

https://github.com/julfrey/detailview

공식 코드

Benchmarking tree species classification from proximally-sensed laser scanning data: introducing the FOR-species20K dataset

https://github.com/juliagast/tgb2

공식 코드

TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs

https://github.com/julianagonzalezastudillo/netfeat

공식 코드

Feature interpretability in BCIs: exploring the role of network lateralization

https://github.com/juliendenize/eztorch

공식 코드

COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformers

https://github.com/jun-cen/cmdfusion

공식 코드

CMDFusion: Bidirectional Fusion Network with Cross-modality Knowledge Distillation for LIDAR Semantic Segmentation

https://github.com/junchenzhi/logic-lncl

공식 코드

Learning from Noisy Crowd Labels with Logics

https://github.com/jungokasai/deep-shallow

공식 코드

Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translation

https://github.com/jungwoo4021/os-kdft

공식 코드

One-Step Knowledge Distillation and Fine-Tuning in Using Large Pre-Trained Self-Supervised Learning Models for Speaker Verification

https://github.com/junhongmit/H2GB

공식 코드

When Heterophily Meets Heterogeneity: Challenges and a New Large-Scale Graph Benchmark

https://github.com/junjie99/mlvu

공식 코드

MLVU: Benchmarking Multi-task Long Video Understanding

https://github.com/jusperlee/audiotrust

공식 코드

AudioTrust: Benchmarking the Multifaceted Trustworthiness of Audio Large Language Models

https://github.com/justinkay/aldi

공식 코드

Align and Distill: Unifying and Improving Domain Adaptive Object Detection

https://github.com/justinwjl/gtb-dti

공식 코드

Benchmark on Drug Target Interaction Modeling from a Structure Perspective

https://github.com/juyongjiang/barec

공식 코드

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

https://github.com/jviquerat/beacon

공식 코드

Beacon, a lightweight deep reinforcement learning benchmark library for flow control

https://github.com/jwaladhamala/BOLD-Bias-in-open-ended-language-generation

공식 코드

BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation

https://github.com/jwc-rad/mislight

공식 코드

Knowledge Distillation from Cross Teaching Teachers for Efficient Semi-Supervised Abdominal Organ Segmentation in CT

https://github.com/jwliang007/ikd

공식 코드

Exploring Inconsistent Knowledge Distillation for Object Detection with Data Augmentation

https://github.com/jxzhanggg/DistillAV

공식 코드

Audio-Visual Representation Learning via Knowledge Distillation from Speech Foundation Models

https://github.com/jybai/generative-memorization-benchmark

공식 코드

On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale Competition

https://github.com/k-stacke/ssl-pathology

공식 코드

Learning Representations with Contrastive Self-Supervised Learning for Histopathology Applications

https://github.com/k2-fsa/icefall

공식 코드

Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation

https://github.com/kacperChwialkowski/wildBootstrap

공식 코드

A Wild Bootstrap for Degenerate Kernel Tests

https://github.com/kaczmarj/champkit

공식 코드

Evaluating histopathology transfer learning with ChampKit

https://github.com/kaggarwal/ganRegression

공식 코드

Benchmarking Regression Methods: A comparison with CGAN

https://github.com/kahno/feature_embedding

공식 코드

Feature embedding in click-through rate prediction

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