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/OedonLestrange42/webnovelbench
WebNovelBench: Placing LLM Novelists on the Web Novel Distribution
https://github.com/OpenNeuroDatasets/ds001499
https://github.com/OrangeSodahub/RMMDet
RMMDet: Road-Side Multitype and Multigroup Sensor Detection System for Autonomous Driving
https://github.com/OzHsu23/chineseocr
COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images
https://github.com/PKU-Alignment/ProAgent
Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination
https://github.com/POSTECH-CVLab/circlegan
CircleGAN: Generative Adversarial Learning across Spherical Circles
https://github.com/PacktPublishing/Hands-On-Image-Generation-with-TensorFlow-2.0/tree/master/Chapter04
https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/t5
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
https://github.com/PaddlePaddle/PaddleOCR
Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition
https://github.com/PengyiZhang/MIADeepSSL
https://github.com/Peter-Devine/multilingual_mt_bench
LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset
https://github.com/Phimos/Paddle-Colorization
https://github.com/Podidiving/lgsc-for-fas-pytorch
https://github.com/PolarNick239/OOCSurfaceReconstructionPaper
Out-of-Core Surface Reconstruction via Global $TGV$ Minimization
https://github.com/Proxim123/person-reID-No1-
https://github.com/QData/TextAttack/blob/master/textattack/attack_recipes/genetic_algorithm_alzantot_2018.py
https://github.com/QiaoLiuHit/LSOTB-TIR
LSOTB-TIR:A Large-Scale High-Diversity Thermal Infrared Object Tracking Benchmark
https://github.com/RAF96/ifmo-2019-deep-learning-coursework
DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data
https://github.com/RUCAIBox/R1-Searcher
SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis
https://github.com/Ram81/AC-VAEGAN-PyTorch
https://github.com/RashadGarayev/ColorizeImage
https://github.com/Recognito-Vision/Android-FaceRecognition-FaceLivenessDetection
FeatherNets: Convolutional Neural Networks as Light as Feather for Face Anti-spoofing
https://github.com/Recognito-Vision/Face-SDK-Linux-Demos
Wild Face Anti-Spoofing Challenge 2023: Benchmark and Results
https://github.com/Recognito-Vision/Linux-FaceRecognition-FaceLivenessDetection
VLAD-VSA: Cross-Domain Face Presentation Attack Detection with Vocabulary Separation and Adaptation
https://github.com/RossNordby/SoftPromptsForEvaluation
The Pile: An 800GB Dataset of Diverse Text for Language Modeling
https://github.com/SEntiMoji/SEntiMoji
https://github.com/SK-tklab/RandomFourierFeatures
Batched Large-scale Bayesian Optimization in High-dimensional Spaces
https://github.com/SSS135/aiqn-vae
https://github.com/SUPERSHOPxyz/stylegan3-gradient
https://github.com/SZU-VCC/RTRecon
CLR-Wire: Towards Continuous Latent Representations for 3D Curve Wireframe Generation
https://github.com/SakiRinn/mindspore-hp-vae-gan
Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample
https://github.com/SarthakTiwari/Rationales-extaction-from-active-molecules
Multi-Objective Molecule Generation using Interpretable Substructures
https://github.com/SaverioMonaco/Image-Colorization-through-Segmentation
https://github.com/SaverioMonaco/ImageColorization
https://github.com/SaverioMonaco/VisionProject
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.