Papers with Code 아카이브

Diversity

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 0
보존된 평가 기록: 0

Diversity in data sampling is crucial across various use cases, including search, recommendation systems, and more. Ensuring diverse samples means capturing a wide range of variations and perspectives, which leads to more robust, unbiased, and comprehensive models. In search use cases, for instance, diversity helps avoid redundancy, ensuring that users are exposed to a broader set of relevant information rather than repeated similar results.

코드

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

https://github.com/zisci2/RethinkKD

공식 코드

Why does Knowledge Distillation Work? Rethink its Attention and Fidelity Mechanism

https://github.com/zixiangzhou916/mdsc

공식 코드

MDSC: Towards Evaluating the Style Consistency Between Music and Dance

https://github.com/zixiangzhou916/ude

공식 코드

UDE: A Unified Driving Engine for Human Motion Generation

https://github.com/zjlab-ammi/lsd

공식 코드

Adversarial Ensemble Training by Jointly Learning Label Dependencies and Member Models

https://github.com/zjowowen/FuncGenFoil

공식 코드

FuncGenFoil: Airfoil Generation and Editing Model in Function Space

https://github.com/zju-pi/awesome-conditional-diffusion-models

공식 코드

Conditional Image Synthesis with Diffusion Models: A Survey

https://github.com/zju-pi/awesome-diffusion-generated-image-detection

공식 코드

Recent Advances on Generalizable Diffusion-generated Image Detection

https://github.com/zju-vipa/DataFree

공식 코드

Contrastive Model Inversion for Data-Free Knowledge Distillation

https://github.com/zju3dv/gcasp

공식 코드

Generative Category-Level Shape and Pose Estimation with Semantic Primitives

https://github.com/zjunet/GPIA_NIPS

공식 코드

Can Graph Neural Networks Expose Training Data Properties? An Efficient Risk Assessment Approach

https://github.com/zjunlp/Revisit-KNN

공식 코드

Revisiting k-NN for Fine-tuning Pre-trained Language Models

https://github.com/zjy0401/cocoformer

공식 코드

CoCoFormer: A controllable feature-rich polyphonic music generation method

https://github.com/zjysteven/DVERGE

공식 코드

DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles

https://github.com/zkzhang98/coinseg

공식 코드

CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentation

https://github.com/zlinao/Variational-Transformer

공식 코드

Variational Transformers for Diverse Response Generation

https://github.com/zmhh-h/fima

공식 코드

Fine-Grained Spatiotemporal Motion Alignment for Contrastive Video Representation Learning

https://github.com/zobia111/sdg-alzheimer

공식 코드

Single Domain Generalization for Alzheimer's Detection from 3D MRIs with Pseudo-Morphological Augmentations and Contrastive Learning

https://github.com/zohreh-aaa/dnn-testing

공식 코드

Black-Box Testing of Deep Neural Networks Through Test Case Diversity

https://github.com/zohrehghaderi/vasta

공식 코드

Diverse Video Captioning by Adaptive Spatio-temporal Attention

https://github.com/zonems/enko

공식 코드

Ensemble Kalman Variational Objectives: Nonlinear Latent Trajectory Inference with A Hybrid of Variational Inference and Ensemble Kalman Filter

https://github.com/zongqianwu/breadth

공식 코드

Is Depth All You Need? An Exploration of Iterative Reasoning in LLMs

https://github.com/zss233-21/hypertuner

공식 코드

HyperTuner: A Cross-Layer Multi-Objective Hyperparameter Auto-Tuning Framework for Data Analytic Services

https://github.com/zsyzzsoft/co-mod-gan

공식 코드

Large Scale Image Completion via Co-Modulated Generative Adversarial Networks

https://github.com/ztt1024/logo-ssl

공식 코드

Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategy

https://github.com/zurichnlp/bless

공식 코드

BLESS: Benchmarking Large Language Models on Sentence Simplification

https://github.com/zwang78/kecae

공식 코드

Key-Exchange Convolutional Auto-Encoder for Data Augmentation in Early Knee Osteoarthritis Detection

https://github.com/zweifel/Physis-Shard

공식 코드

Spectrum-Diverse Neuroevolution with Unified Neural Models

https://github.com/zwhong714/adaptive_decoding

공식 코드

Improving Open-Ended Text Generation via Adaptive Decoding

https://github.com/zwyang6/unia

공식 코드

Tackling Ambiguity from Perspective of Uncertainty Inference and Affinity Diversification for Weakly Supervised Semantic Segmentation

https://github.com/zychowskia/icoevordf

공식 코드

Cultivating Archipelago of Forests: Evolving Robust Decision Trees through Island Coevolution

https://github.com/zyn213/temprmot

공식 코드

Bootstrapping Referring Multi-Object Tracking

https://github.com/zzbuzzard/guidediffuseq

공식 코드

Understanding the Quality-Diversity Trade-off in Diffusion Language Models

https://github.com/zzhangsm/ookd

공식 코드

Revisiting Knowledge Distillation under Distribution Shift

https://github.com/zzjchen/qube_code

공식 코드

QUBE: Enhancing Automatic Heuristic Design via Quality-Uncertainty Balanced Evolution

https://github.com/zzq-bot/romance

공식 코드

Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers

https://gitlab.com/2factor/QDSurprise

공식 코드

Quality Diversity Through Surprise

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