Data Augmentation
تعزيز البيانات
تقنيات لتوسيع مجموعة التدريب بتوليد نسخ مُحوَّرة من البيانات الأصلية (قص، قلب، تغيير ألوان). الأساليب التقابلية تعتمد عليها بشدة، بينما MAE يستغني عنها لأن التقنيع العشوائي يؤدي دورها.
Techniques to expand the training set by generating transformed copies of original data (cropping, flipping, color jittering). Contrastive methods depend heavily on them, while MAE does not need them because random masking serves the same purpose.
Also translated asإثراء البيانات، إثراء مصفوفات التدريب اصطناعياً، توسيع المعطيات بالتحوير الهندسي، توليد وتوليف البيانات، زيادة البيانات
First appears in this corpus in: No Free Lunch Theorems for Optimization (1997)
Appears in these papers
- ImageNet Classification with Deep Convolutional Neural Networks2012in the sky ✦
- ALIGN: Scaling Up Visual and Vision-Language Representation Learning with Noisy Text Supervision2021in the sky ✦
- Alpaca: A Strong, Replicable Instruction-Following Model2023in the sky ✦
- A General Reinforcement Learning Algorithm That Masters Chess, Shogi, and Go Through Self-Play2018in the sky ✦
- Barlow Twins: Self-Supervised Learning via Redundancy Reduction2021in the sky ✦
- Barlow Twins: Self-Supervised Learning via Redundancy Reduction2021in the sky ✦
- Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning2020in the sky ✦
- Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning2020in the sky ✦
- Chronos: Learning the Language of Time Series2024in the sky ✦
- Chronos: Learning the Language of Time Series2024in the sky ✦
- Contriever: Unsupervised Dense Information Retrieval with Contrastive Learning2022in the sky ✦
- A ConvNet for the 2020s2022in the sky ✦
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017in the sky ✦
- Deep Speech 2: End-to-End Speech Recognition in English and Mandarin2015in the sky ✦
- Deep Speech 2: End-to-End Speech Recognition in English and Mandarin2015in the sky ✦
- Deformable Convolutional Networks2017in the sky ✦
- Training Data-Efficient Image Transformers & Distillation Through Attention2021in the sky ✦
- Training Data-Efficient Image Transformers & Distillation Through Attention2021in the sky ✦
- Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data2024in the sky ✦
- Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data2024in the sky ✦
- Emerging Properties in Self-Supervised Vision Transformers2021in the sky ✦
- Emerging Properties in Self-Supervised Vision Transformers2021in the sky ✦
- DINOv2: Learning Robust Visual Features Without Supervision2023in the sky ✦
- Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World2017in the sky ✦
- Dropout: A Simple Way to Prevent Neural Networks from Overfitting2014in the sky ✦
- Generative Adversarial Networks2014in the sky ✦
- Graph Attention Networks2018in the sky ✦
- Symbolic Discovery of Optimization Algorithms2023in the sky ✦
- Masked Autoencoders Are Scalable Vision Learners2022in the sky ✦
- mixup: Beyond Empirical Risk Minimization2018in the sky ✦
- mixup: Beyond Empirical Risk Minimization2018in the sky ✦
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications2017in the sky ✦
- Momentum Contrast for Unsupervised Visual Representation Learning2020in the sky ✦
- No Free Lunch Theorems for Optimization1997in the sky ✦
- Perceiver: General Perception with Iterative Attention2021in the sky ✦
- Textbooks Are All You Need2023in the sky ✦
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation2017in the sky ✦
- Unsupervised Representation Learning by Predicting Image Rotations2018in the sky ✦
- RT-1: Robotics Transformer for Real-World Control at Scale2022in the sky ✦
- Self-Instruct: Aligning Language Models with Self-Generated Instructions2022in the sky ✦
- A Simple Framework for Contrastive Learning of Visual Representations2020in the sky ✦
- A Simple Framework for Contrastive Learning of Visual Representations2020in the sky ✦
- Exploring Simple Siamese Representation Learning2021in the sky ✦
- Exploring Simple Siamese Representation Learning2021in the sky ✦
- Video Generation Models as World Simulators2024in the sky ✦
- Spatial Transformer Networks2015in the sky ✦
- SSD: Single Shot MultiBox Detector2016in the sky ✦
- SwAV: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments2020in the sky ✦
- SwAV: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments2020in the sky ✦
- Toolformer: Language Models Can Teach Themselves to Use Tools2023in the sky ✦
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015in the sky ✦
- Very Deep Convolutional Networks for Large-Scale Image Recognition2014in the sky ✦
- VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning2021in the sky ✦
- Robust Speech Recognition via Large-Scale Weak Supervision2022in the sky ✦
- You Only Look Once: Unified, Real-Time Object Detection2015in the sky ✦