Papers with Code 아카이브
Diversity
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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/gallorob/dynamic-quality-diversity
공식 코드https://github.com/gaobb/MCAR
공식 코드Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition
https://github.com/garywei944/chemflow
공식 코드https://github.com/gasolsun36/apollo
공식 코드APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning
https://github.com/gastruc/anysat
공식 코드AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalities
https://github.com/gastruc/omnisat
공식 코드OmniSat: Self-Supervised Modality Fusion for Earth Observation
https://github.com/gatech-sysml/CompOFA
공식 코드CompOFA: Compound Once-For-All Networks for Faster Multi-Platform Deployment
https://github.com/gauchm/ealstm_regional_modeling
공식 코드The Proper Care and Feeding of CAMELS: How Limited Training Data Affects Streamflow Prediction
https://github.com/gautamMalu/Aesthetic_attributes_maps
공식 코드https://github.com/gc-js/creopep
공식 코드CreoPep: A Universal Deep Learning Framework for Target-Specific Peptide Design and Optimization
https://github.com/gchochla/vault
공식 코드VAuLT: Augmenting the Vision-and-Language Transformer for Sentiment Classification on Social Media
https://github.com/gcorso/particle-guidance
공식 코드Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models
https://github.com/gdemos01/fab-2024
공식 코드https://github.com/gdtreebank/gdtreebank
공식 코드The Galactic Dependencies Treebanks: Getting More Data by Synthesizing New Languages
https://github.com/geek-ai/Texygen
공식 코드https://github.com/geekan/metagpt
공식 코드SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learning
https://github.com/gemcollector/TLDA
공식 코드Don't Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement Learning
https://github.com/genentech/ringer
공식 코드https://github.com/gentlesjan/affordpose
공식 코드AffordPose: A Large-scale Dataset of Hand-Object Interactions with Affordance-driven Hand Pose
https://github.com/georgiarg/autofashion
공식 코드Automatic Generation of Fashion Images using Prompting in Generative Machine Learning Models
https://github.com/gestaltcogteam/basicts
공식 코드BLAST: Balanced Sampling Time Series Corpus for Universal Forecasting Models
https://github.com/gestaltcogteam/blast
공식 코드BLAST: Balanced Sampling Time Series Corpus for Universal Forecasting Models
https://github.com/gfnorg/gflownet
공식 코드https://github.com/gfnorg/gfn_vs_hvi
공식 코드https://github.com/gfnorg/multi-objective-gfn
공식 코드https://github.com/ghupppp/memorysharingllm
공식 코드https://github.com/giacoballoccu/explanation-quality-recsys
공식 코드https://github.com/giladcohen/arf
공식 코드Simple Post-Training Robustness Using Test Time Augmentations and Random Forest
https://github.com/giladcohen/katana
공식 코드Simple Post-Training Robustness Using Test Time Augmentations and Random Forest
https://github.com/gimpong/AAAI22-MeCoQ
공식 코드Contrastive Quantization with Code Memory for Unsupervised Image Retrieval
https://github.com/gingasan/lemon
공식 코드Rethinking Masked Language Modeling for Chinese Spelling Correction
https://github.com/giorgiop/loss-correction
공식 코드Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach
https://github.com/git-disl/Chameleon
공식 코드Personalized Privacy Protection Mask Against Unauthorized Facial Recognition
https://github.com/git-disl/EnsembleBench
공식 코드Promoting High Diversity Ensemble Learning with EnsembleBench
https://github.com/git-disl/HQ-Ensemble
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.