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/yumingj/Text2Human
공식 코드https://github.com/yumingj/deepfashion-multimodal
공식 코드https://github.com/yunglau/QGFN
공식 코드https://github.com/yunguo224/lhp-rain
공식 코드From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain Removal
https://github.com/yunxiangfu2001/dreamda
공식 코드https://github.com/yupeilin2388/diff-mosaic
공식 코드https://github.com/yuweiyin/ttida
공식 코드TTIDA: Controllable Generative Data Augmentation via Text-to-Text and Text-to-Image Models
https://github.com/yuyang-long/ssa
공식 코드https://github.com/yuyujunjun/rsmt-realtime-stylized-motion-transition
공식 코드https://github.com/yuzhimanhua/seetopic
공식 코드https://github.com/yw0208/W-HMR
공식 코드W-HMR: Monocular Human Mesh Recovery in World Space with Weak-Supervised Calibration
https://github.com/yx-cloud/grug
공식 코드Unifying gradient regularization for Heterogeneous Graph Neural Networks
https://github.com/yxjdarren/mvdscn
공식 코드https://github.com/yxntu/generaldyg
공식 코드https://github.com/yxuansu/contrastive_search_versus_contrastive_decoding
공식 코드An Empirical Study On Contrastive Search And Contrastive Decoding For Open-ended Text Generation
https://github.com/yxuansu/plangen
공식 코드Plan-then-Generate: Controlled Data-to-Text Generation via Planning
https://github.com/yxuansu/simctg
공식 코드https://github.com/yyjmjc/compositional-temporal-grounding
공식 코드Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning
https://github.com/yymgch/cycle-chaos-gan
공식 코드https://github.com/yytzsy/smcg
공식 코드https://github.com/yytzsy/syntax-customized-video-captioning
공식 코드Syntax Customized Video Captioning by Imitating Exemplar Sentences
https://github.com/yzichen/mmlanedet
공식 코드DALNet: A Rail Detection Network Based on Dynamic Anchor Line
https://github.com/zackschen/cucl
공식 코드https://github.com/zanchangtong/ptvsri
공식 코드https://github.com/zangzelin/code_usd
공식 코드USD: Unsupervised Soft Contrastive Learning for Fault Detection in Multivariate Time Series
https://github.com/zd11024/entity_questioner
공식 코드Enhancing Visual Dialog Questioner with Entity-based Strategy Learning and Augmented Guesser
https://github.com/zdk258/TokenSwap
공식 코드Exploring Token-Level Augmentation in Vision Transformer for Semi-Supervised Semantic Segmentation
https://github.com/zechao-guan/topodit-3d
공식 코드https://github.com/zedian/hyperlora
공식 코드https://github.com/zehao-wang/indoortraj
공식 코드Diversity-Driven View Subset Selection for Indoor Novel View Synthesis
https://github.com/zeinsh/lenta_short_sentences
공식 코드https://github.com/zelongzeng/rwpm
공식 코드Random Walk on Pixel Manifolds for Anomaly Segmentation of Complex Driving Scenes
https://github.com/zengqunzhao/aim-fair
공식 코드https://github.com/zenquiorra/m3ls
공식 코드https://github.com/zenseact/zod
공식 코드Zenseact Open Dataset: A large-scale and diverse multimodal dataset for autonomous driving
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.