https://gitlab.com/adriaruizo/dhne-aaai21
공식 코드Anytime Inference with Distilled Hierarchical Neural Ensembles
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Anytime Inference with Distilled Hierarchical Neural Ensembles
Unsupervised Boosting-based Autoencoder Ensembles for Outlier Detection
Behind Recommender Systems: the Geography of the ACM RecSys Community
Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context
XCAT-3.0: A Comprehensive Library of Personalized Digital Twins Derived from CT Scans
MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation
Unifying Human and Statistical Evaluation for Natural Language Generation
On Redundancy and Diversity in Cell-based Neural Architecture Search
eProduct: A Million-Scale Visual Search Benchmark to Address Product Recognition Challenges
Accelerating Prototype-Based Drug Discovery using Conditional Diversity Networks
PSP: Million-level Protein Sequence Dataset for Protein Structure Prediction
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
SRFlow: Learning the Super-Resolution Space with Normalizing Flow
Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding
Diversified Arbitrary Style Transfer via Deep Feature Perturbation
Scene Text Detection with Supervised Pyramid Context Network
Ego2Hands: A Dataset for Egocentric Two-hand Segmentation and Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.