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/sapienzanlp/leakdistill

공식 코드

Incorporating Graph Information in Transformer-based AMR Parsing

https://github.com/saptarshi059/cdqa-v1-targetted-pretraining

공식 코드

TOP-Training: Target-Oriented Pretraining for Medical Extractive Question Answering

https://github.com/sariyanidi/M3DFB

공식 코드

3D Face Reconstruction Error Decomposed: A Modular Benchmark for Fair and Fast Method Evaluation

https://github.com/sarthaxxxxx/av-c-robustness-benchmark

공식 코드

$\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time

https://github.com/sarwanpasha/adversarial_attack_on_biological_sequences

공식 코드

Benchmarking Machine Learning Robustness in Covid-19 Genome Sequence Classification

https://github.com/satgoy152/ling_llm

공식 코드

IOLBENCH: Benchmarking LLMs on Linguistic Reasoning

https://github.com/satoru2001/cukdfir

공식 코드

Context Unaware Knowledge Distillation for Image Retrieval

https://github.com/sbelharbi/sr-caco-2

공식 코드

SR-CACO-2: A Dataset for Confocal Fluorescence Microscopy Image Super-Resolution

https://github.com/sbi-benchmark/sbibm

공식 코드

Benchmarking Simulation-Based Inference

https://github.com/sbysbysbys/afov

공식 코드

3D Annotation-Free Learning by Distilling 2D Open-Vocabulary Segmentation Models for Autonomous Driving

https://github.com/sbysbysbys/uov

공식 코드

3D Annotation-Free Learning by Distilling 2D Open-Vocabulary Segmentation Models for Autonomous Driving

https://github.com/schaepermeier/moleopt

공식 코드

MOLE: Digging Tunnels Through Multimodal Multi-Objective Landscapes

https://github.com/schaepermeier/r2-revisited

공식 코드

Reinvestigating the R2 Indicator: Achieving Pareto Compliance by Integration

https://github.com/schmidt-ju/argoverse-navmap

공식 코드

Exploring Navigation Maps for Learning-Based Motion Prediction

https://github.com/schmitt-muc/SEN12MS

공식 코드

Remote Sensing Image Classification with the SEN12MS Dataset

https://github.com/schneiderkamplab/syntheval

공식 코드

SynthEval: A Framework for Detailed Utility and Privacy Evaluation of Tabular Synthetic Data

https://github.com/schuture/benchmarking-awesome-diffusion-models

공식 코드

X-IQE: eXplainable Image Quality Evaluation for Text-to-Image Generation with Visual Large Language Models

https://github.com/schuture/deeptumorvqa

공식 코드

Are Vision Language Models Ready for Clinical Diagnosis? A 3D Medical Benchmark for Tumor-centric Visual Question Answering

https://github.com/sci-assess/sciassess

공식 코드

SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysis

https://github.com/scikit-adaptation/skada-bench

공식 코드

SKADA-Bench: Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation On Diverse Modalities

https://github.com/scmaree/HillVallEA

공식 코드

Benchmarking the Hill-Valley Evolutionary Algorithm for the GECCO 2018 Competition on Niching Methods Multimodal Optimization

https://github.com/scnu-rislab/kdmos

공식 코드

KDMOS:Knowledge Distillation for Motion Segmentation

https://github.com/scok30/vit-cil

공식 코드

Fine-Grained Knowledge Selection and Restoration for Non-Exemplar Class Incremental Learning

https://github.com/scottclowe/zs-ssl-clustering

공식 코드

An Empirical Study into Clustering of Unseen Datasets with Self-Supervised Encoders

https://github.com/scut-dlvclab/megahan97k

공식 코드

MegaHan97K: A Large-Scale Dataset for Mega-Category Chinese Character Recognition with over 97K Categories

https://github.com/sdlzy/arc

공식 코드

Joint Answering and Explanation for Visual Commonsense Reasoning

https://github.com/sdnr/RNN-Conv-Decoder

공식 코드

On Recurrent Neural Networks for Sequence-based Processing in Communications

https://github.com/se-hwan/pbrs-humanoid

공식 코드

Benchmarking Potential Based Rewards for Learning Humanoid Locomotion

https://github.com/sea-shunned/hawks

공식 코드

HAWKS: Evolving Challenging Benchmark Sets for Cluster Analysis

https://github.com/sea-shunned/hawks_configs

공식 코드

HAWKS: Evolving Challenging Benchmark Sets for Cluster Analysis

https://github.com/seanzhuh/awesome-open-vocabulary-detection-and-segmentation

공식 코드

A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Future

https://github.com/searchivarius/long_doc_rank_model_analysis

공식 코드

Understanding Performance of Long-Document Ranking Models through Comprehensive Evaluation and Leaderboarding

https://github.com/seatizendoi/zenodo-tools

공식 코드

From underwater to aerial: a novel multi-scale knowledge distillation approach for coral reef monitoring

https://github.com/sebastian-hofstaetter/intra-document-cascade

공식 코드

Intra-Document Cascading: Learning to Select Passages for Neural Document Ranking

https://github.com/sebastian-hofstaetter/neural-ranking-kd

공식 코드

Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation

https://github.com/sebbarb/time_aware_attention

공식 코드

Benchmarking Deep Learning Architectures for Predicting Readmission to the ICU and Describing Patients-at-Risk

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