https://github.com/SikaStar/IDM
공식 코드IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID
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/SimarKareer/EgoMimic
공식 코드https://github.com/Sirui-Xu/DuMMF
공식 코드https://github.com/SliverySky/mariopuzzle
공식 코드Experience-Driven PCG via Reinforcement Learning: A Super Mario Bros Study
https://github.com/Snnzhao/MIDGN
공식 코드Multi-view Intent Disentangle Graph Networks for Bundle Recommendation
https://github.com/Spandan-Madan/generalization_biased_category_pose
공식 코드When and how CNNs generalize to out-of-distribution category-viewpoint combinations
https://github.com/Stanford-ILIAD/DPP-Batch-Active-Learning
공식 코드https://github.com/Stanford-TML/EDGE
공식 코드https://github.com/StonyBrookNLP/attention-sink-cl
공식 코드Does RoBERTa Perform Better than BERT in Continual Learning: An Attention Sink Perspective
https://github.com/StoreyLab/lfa
공식 코드Probabilistic models of genetic variation in structured populations applied to global human studies
https://github.com/SubmissionsIn/SDMVC
공식 코드Self-supervised Discriminative Feature Learning for Deep Multi-view Clustering
https://github.com/SungMinCho/MEANTIME
공식 코드https://github.com/SwinTransformer/MIM-Depth-Estimation
공식 코드https://github.com/SysCV/bdd100k-models
공식 코드BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
https://github.com/TAMU-VITA/ABD-Net
공식 코드https://github.com/TEA-Lab/diffusion_reward
공식 코드Diffusion Reward: Learning Rewards via Conditional Video Diffusion
https://github.com/THUDM/ComiRec
공식 코드https://github.com/TLouf/multiling-twitter
공식 코드https://github.com/TOM-tym/Learn-to-Imagine
공식 코드Learning to Imagine: Diversify Memory for Incremental Learning using Unlabeled Data
https://github.com/Tab-ct/MAP-SNN
공식 코드https://github.com/TakaOsa/adInfoHRL
공식 코드Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization
https://github.com/TanJing94/Deep_Portraits_Correction
공식 코드Practical Wide-Angle Portraits Correction with Deep Structured Models
https://github.com/TangJiaLong/SSD-OpenIE
공식 코드Syntactic and Semantic-driven Learning for Open Information Extraction
https://github.com/TarunTater/AbstractConceptsInImages
공식 코드https://github.com/Tencent/DepthCrafter
공식 코드DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
https://github.com/Tencent/TFace
공식 코드https://github.com/TorchCraft/StarData
공식 코드https://github.com/UARK-AICV/VLCAP
공식 코드VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning
https://github.com/UBC-NLP/marbert
공식 코드ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic
https://github.com/UBCDingXin/cDR-RS
공식 코드Efficient Subsampling of Realistic Images From GANs Conditional on a Class or a Continuous Variable
https://github.com/UKPLab/acl2020-confidence-regularization
공식 코드Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance
https://github.com/UM-ARM-Lab/probabilistic_shape_completion
공식 코드Diverse Plausible Shape Completions from Ambiguous Depth Images
https://github.com/USTCAVSA/TSL
공식 코드https://github.com/Unity-Technologies/AnthroNet
공식 코드AnthroNet: Conditional Generation of Humans via Anthropometrics
https://github.com/Unity-Technologies/com.unity.cv.synthetichumans
공식 코드AnthroNet: Conditional Generation of Humans via Anthropometrics
https://github.com/VITA-MLLM/Sparrow
공식 코드T2Vid: Translating Long Text into Multi-Image is the Catalyst for Video-LLMs
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.