https://github.com/scarelette/culturellm
공식 코드CultureLLM: Incorporating Cultural Differences into Large Language Models
Papers with Code 아카이브
Data Augmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 3
- 보존된 평가 기록
- 26
Data augmentation involves techniques used for increasing the amount of data, based on different modifications, to expand the amount of examples in the original dataset. Data augmentation not only helps to grow the dataset but it also increases the diversity of the dataset. When training machine learning models, data augmentation acts as a regularizer and helps to avoid overfitting.
Data augmentation techniques have been found useful in domains like NLP and computer vision. In computer vision, transformations like cropping, flipping, and rotation are used. In NLP, data augmentation techniques can include swapping, deletion, random insertion, among others.
Further readings:
- A Survey of Data Augmentation Approaches for NLP
- A survey on Image Data Augmentation for Deep Learning
<span style="color:grey; opacity: 0.6">( Image credit: Albumentations )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/schrodingho/fm_zsl_iot
공식 코드https://github.com/schwallergroup/augmented_memory
공식 코드Saturn: Sample-efficient Generative Molecular Design using Memory Manipulation
https://github.com/schwallergroup/saturn
공식 코드Saturn: Sample-efficient Generative Molecular Design using Memory Manipulation
https://github.com/scientific-computing-lab-nrcn/ompify
공식 코드Advising OpenMP Parallelization via a Graph-Based Approach with Transformers
https://github.com/scott-yjyang/hcdg
공식 코드HCDG: A Hierarchical Consistency Framework for Domain Generalization on Medical Image Segmentation
https://github.com/scstech85/DocEmul
공식 코드DocEmul: a Toolkit to Generate Structured Historical Documents
https://github.com/sct-pipeline/contrast-agnostic-softseg-spinalcord
공식 코드Towards contrast-agnostic soft segmentation of the spinal cord
https://github.com/scuwyh2000/diff-ii
공식 코드Inversion Circle Interpolation: Diffusion-based Image Augmentation for Data-scarce Classification
https://github.com/sdemyanov/ConvNet
공식 코드Invariant backpropagation: how to train a transformation-invariant neural network
https://github.com/sdoerrich97/vits-are-generative-models
공식 코드Self-supervised Vision Transformer are Scalable Generative Models for Domain Generalization
https://github.com/sdv4/Predicting-Confusion-with-RNN_HAI-2019
공식 코드Predicting Confusion from Eye-Tracking Data with Recurrent Neural Networks
https://github.com/seanie12/SWEP
공식 코드Learning to Perturb Word Embeddings for Out-of-distribution QA
https://github.com/searecluse/cvprw2024
공식 코드https://github.com/sebastian-steindl/CoPrUS_data
공식 코드CoPrUS: Consistency Preserving Utterance Synthesis towards more realistic benchmark dialogues
https://github.com/sebraun-msr/acd_class_mapping
공식 코드Multi-label audio classification with a noisy zero-shot teacher
https://github.com/seedatnabeel/cllm
공식 코드Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes
https://github.com/seer-lab/augmentationbias
공식 코드Assessing Data Augmentation-Induced Bias in Training and Testing of Machine Learning Models
https://github.com/senmaoy/RAT-Diffusion
공식 코드Data Extrapolation for Text-to-image Generation on Small Datasets
https://github.com/sense-gvt/fast-bev
공식 코드Fast-BEV: Towards Real-time On-vehicle Bird's-Eye View Perception
https://github.com/sense-gvt/sncse
공식 코드SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative Samples
https://github.com/sense-x/tokenmix
공식 코드TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers
https://github.com/seoyeon-p/tdmixup
공식 코드A Data Cartography based MixUp for Pre-trained Language Models
https://github.com/serkansulun/deep-music-enhancer
공식 코드On Filter Generalization for Music Bandwidth Extension Using Deep Neural Networks
https://github.com/servicenow/promptmix-emnlp-2023
공식 코드PromptMix: A Class Boundary Augmentation Method for Large Language Model Distillation
https://github.com/shachardon/prequel
공식 코드PreQuEL: Quality Estimation of Machine Translation Outputs in Advance
https://github.com/shadowtwin41/brats_2023_2024_solutions
공식 코드Improved Multi-Task Brain Tumour Segmentation with Synthetic Data Augmentation
https://github.com/shahriarnz14/temporal-supervised-contrastive-learning
공식 코드Temporal Supervised Contrastive Learning for Modeling Patient Risk Progression
https://github.com/shanmon110/aamsupcon
공식 코드Speaker Representation Learning via Contrastive Loss with Maximal Speaker Separability
https://github.com/sharpiless/nanocrystals-deep-learning
공식 코드https://github.com/sharpiless/nanocrystals-tem-segmentation
공식 코드https://github.com/shashankvkt/alignmixup_cvpr22
공식 코드AlignMixup: Improving Representations By Interpolating Aligned Features
https://github.com/sheffieldnlp/deepQuest-py
공식 코드https://github.com/sheinkmana/V_bowtie_NN
공식 코드https://github.com/shengcheng/aba
공식 코드Adversarial Bayesian Augmentation for Single-Source Domain Generalization
https://github.com/shengrenhou/rl-adn
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.