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/shaoshitong/Catch-Up-Distillation

공식 코드

Catch-Up Distillation: You Only Need to Train Once for Accelerating Sampling

https://github.com/sharc-lab/hlsfactory

공식 코드

HLSFactory: A Framework Empowering High-Level Synthesis Datasets for Machine Learning and Beyond

https://github.com/sharif-apu/lsd-tfformer

공식 코드

Illuminating Darkness: Enhancing Real-world Low-light Scenes with Smartphone Images

https://github.com/sharifamit/rfrl-net

공식 코드

Feature Representation Learning for Robust Retinal Disease Detection from Optical Coherence Tomography Images

https://github.com/shark-nlp/cab

공식 코드

CAB: Comprehensive Attention Benchmarking on Long Sequence Modeling

https://github.com/sharpiless/rgal

공식 코드

Relation-Guided Adversarial Learning for Data-free Knowledge Transfer

https://github.com/shashankskagnihotri/adv-corrected-ddcat-cospgd

공식 코드

CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks

https://github.com/shashankskagnihotri/benchmarking_reliability_generalization

공식 코드

SemSegBench & DetecBench: Benchmarking Reliability and Generalization Beyond Classification

https://github.com/shashankskagnihotri/benchmarking_robustness

공식 코드

Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?

https://github.com/shashankskagnihotri/cospgd

공식 코드

CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks

https://github.com/shashidharjavaji/RC_BENCH

공식 코드

Can AI Validate Science? Benchmarking LLMs for Accurate Scientific Claim $\rightarrow$ Evidence Reasoning

https://github.com/shaunak27/grain-clip

공식 코드

Grounding Descriptions in Images informs Zero-Shot Visual Recognition

https://github.com/shawnan-whu/choice

공식 코드

CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Models

https://github.com/sheffieldnlp/deepQuest-py

공식 코드

Knowledge Distillation for Quality Estimation

https://github.com/shehzaadzd/MINERVA

공식 코드

Neuro-Symbolic Inductive Logic Programming with Logical Neural Networks

https://github.com/shen9712/universaladapterlearning

공식 코드

Language-Universal Adapter Learning with Knowledge Distillation for End-to-End Multilingual Speech Recognition

https://github.com/shenyanghuang/tgb

공식 코드

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

https://github.com/shicaiwei123/sdd-cvpr2024

공식 코드

Scale Decoupled Distillation

https://github.com/shijiangming1/clip2fl

공식 코드

CLIP-guided Federated Learning on Heterogeneous and Long-Tailed Data

https://github.com/shijianjian/ImmersePro

공식 코드

ImmersePro: End-to-End Stereo Video Synthesis Via Implicit Disparity Learning

https://github.com/shijieS/SST

공식 코드

Deep Affinity Network for Multiple Object Tracking

https://github.com/shijieS/people-counting-dataset

공식 코드

Benchmark data and method for real-time people counting in cluttered scenes using depth sensors

https://github.com/shilin-lu/vine

공식 코드

Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances

https://github.com/shimazaki/pnlss

공식 코드

A projected nonlinear state-space model for forecasting time series signals

https://github.com/shimhz/a_dcf

공식 코드

a-DCF: an architecture agnostic metric with application to spoofing-robust speaker verification

https://github.com/shiqiyu/opengait

공식 코드

LidarGait: Benchmarking 3D Gait Recognition with Point Clouds

https://github.com/shivangi-aneja/COSMOS

공식 코드

COSMOS: Catching Out-of-Context Misinformation with Self-Supervised Learning

https://github.com/shiyegao/Self-Contradictory-Instructions-SCI

공식 코드

Dissecting Dissonance: Benchmarking Large Multimodal Models Against Self-Contradictory Instructions

https://github.com/shl5133/E2EECPE

공식 코드

End-to-end Emotion-Cause Pair Extraction via Learning to Link

https://github.com/shovito66/GlucoNet

공식 코드

Hybrid Attention Model Using Feature Decomposition and Knowledge Distillation for Glucose Forecasting

https://github.com/showlab/macosworld

공식 코드

macOSWorld: A Multilingual Interactive Benchmark for GUI Agents

https://github.com/shuaizhao95/Unlearning

공식 코드

Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation

https://github.com/shubha07m/Energy-optimized-semantic-loss

공식 코드

Transformers for Green Semantic Communication: Less Energy, More Semantics

https://github.com/shubha07m/MetaGreen-Meta-Learning-Inspired-Transformer-Selection

공식 코드

MetaGreen: Meta-Learning Inspired Transformer Selection for Green Semantic Communication

https://github.com/shubhamagarwal12/warlearn

공식 코드

WARLearn: Weather-Adaptive Representation Learning

https://github.com/shufangxun/llava-mod

공식 코드

LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation

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