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/ddursun/violence-detection

공식 코드

Comparative Analysis: Violence Recognition from Videos using Transfer Learning

https://github.com/dearbreeze/reviewkd

공식 코드

Reducing Capacity Gap in Knowledge Distillation with Review Mechanism for Crowd Counting

https://github.com/debarshikundupsu/scifaultyqa

공식 코드

SciFaultyQA: Benchmarking LLMs on Faulty Science Question Detection with a GAN-Inspired Approach to Synthetic Dataset Generation

https://github.com/debeshjha/gastrovision

공식 코드

GastroVision: A Multi-class Endoscopy Image Dataset for Computer Aided Gastrointestinal Disease Detection

https://github.com/deborahmit/TasteNet-MNL

공식 코드

A Neural-embedded Choice Model: TasteNet-MNL Modeling Taste Heterogeneity with Flexibility and Interpretability

https://github.com/decisionforce/metadrive

공식 코드

MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning

https://github.com/decisionintelligence/tab

공식 코드

TAB: Unified Benchmarking of Time Series Anomaly Detection Methods

https://github.com/decisionintelligence/tfb

공식 코드

TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods

https://github.com/declare-lab/knot

공식 코드

KNOT: Knowledge Distillation using Optimal Transport for Solving NLP Tasks

https://github.com/declare-lab/segue

공식 코드

Sentence Embedder Guided Utterance Encoder (SEGUE) for Spoken Language Understanding

https://github.com/declare-lab/sinkhorn-loss

공식 코드

KNOT: Knowledge Distillation using Optimal Transport for Solving NLP Tasks

https://github.com/declipsonator/gptzzzs

공식 코드

Authorship Obfuscation in Multilingual Machine-Generated Text Detection

https://github.com/dedeswim/timm-adv-training

공식 코드

Scaling Compute Is Not All You Need for Adversarial Robustness

https://github.com/deep-optimization/scalekd

공식 코드

ScaleKD: Strong Vision Transformers Could Be Excellent Teachers

https://github.com/deep500/deep500

공식 코드

A Modular Benchmarking Infrastructure for High-Performance and Reproducible Deep Learning

https://github.com/deepcomm/kocodes

공식 코드

KO codes: Inventing Nonlinear Encoding and Decoding for Reliable Wireless Communication via Deep-learning

https://github.com/deepfakeil/dfil

공식 코드

DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery Clues

https://github.com/deepintostreams/spde_hackathon

공식 코드

SPDEBench: An Extensive Benchmark for Learning Regular and Singular Stochastic PDEs

https://github.com/deepmicroscopy/ami-br_benchmark

공식 코드

Benchmarking Deep Learning and Vision Foundation Models for Atypical vs. Normal Mitosis Classification with Cross-Dataset Evaluation

https://github.com/deepmind/dm_hamiltonian_dynamics_suite

공식 코드

Which priors matter? Benchmarking models for learning latent dynamics

https://github.com/deepmind/image_obfuscation_benchmark

공식 코드

Benchmarking Robustness to Adversarial Image Obfuscations

https://github.com/deepopinion/greedy-layer-pruning

공식 코드

Greedy-layer Pruning: Speeding up Transformer Models for Natural Language Processing

https://github.com/deepreasoning/neulr

공식 코드

Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond

https://github.com/delchiaro/RATT

공식 코드

RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning

https://github.com/demidovd98/med_lowdata

공식 코드

Distilling Local Texture Features for Colorectal Tissue Classification in Low Data Regimes

https://github.com/dennisliu2022/membership-inference-attacks-by-exploiting-loss-trajectory

공식 코드

Membership Inference Attacks by Exploiting Loss Trajectory

https://github.com/derekabc/cottonweeds

공식 코드

Performance Evaluation of Deep Transfer Learning on Multiclass Identification of Common Weed Species in Cotton Production Systems

https://github.com/deriq-qian-dong/iii-retriever

공식 코드

I^3 Retriever: Incorporating Implicit Interaction in Pre-trained Language Models for Passage Retrieval

https://github.com/desehuileng0o0/ikem

공식 코드

Elevating Skeleton-Based Action Recognition with Efficient Multi-Modality Self-Supervision

https://github.com/design-bench/design-bench.github.io

공식 코드

DEsignBench: Exploring and Benchmarking DALL-E 3 for Imagining Visual Design

https://github.com/deu30303/feddefender

공식 코드

FedDefender: Client-Side Attack-Tolerant Federated Learning

https://github.com/devavrattomar/tesla

공식 코드

TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation

https://github.com/devindeng94/smac-hard

공식 코드

SMAC-Hard: Enabling Mixed Opponent Strategy Script and Self-play on SMAC

https://github.com/dhopp1/nowcasting_benchmark

공식 코드

Benchmarking Econometric and Machine Learning Methodologies in Nowcasting

https://github.com/diabolocom-research/conversationaldataset

공식 코드

ASR Benchmarking: Need for a More Representative Conversational Dataset

https://github.com/diagnijmegen/hover-unet

공식 코드

HoVer-UNet: Accelerating HoVerNet with UNet-based multi-class nuclei segmentation via knowledge distillation

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