Glossary

0-9

0-shot learning 1-shot learning 2-stage detector 3D convolution 4D data 5G + AI 6DoF pose estimation 7D representation 8-bit quantization 9-layer network

A

AGI / Artificial General Intelligence Algorithm Artificial Intelligence (AI)Attention Autoencoder

B

Backpropagation Batch Normalization BERT Bias Boosting

C

Chatbot Classifier / Classification Clustering CNN / Convolutional Neural Network Cross-Validation

D

Data Augmentation Deep Learning Deepfake Deterministic Model Discriminative Model

E

Embedding Encoder Ensemble Learning Epoch Explainable AI (XAI)

F

Feature Extraction Fine-tuning Forward Propagation Foundation Model Fusion / Multimodal Fusion

G

GAN / Generative Adversarial Network Generative AI Gradient Descent Graph Neural Network (GNN)Grounding

H

Hallucination Heuristic Hidden Layer Hierarchical Model Hyperparameter

I

Imbalanced Data Instance / Sample Instruction tuning Intelligence Amplification / Augmentation Interpretability

J

JAX Jittering Joint Embedding JSONL / JSON-lines Juxtaposition

K

K-means Clustering K-Shot Learning Kernel Trick KL Divergence (Kullback–Leibler Divergence)Knowledge Distillation

L

Large Language Model (LLM)Latent Variable Learning Rate Loss Function LSTM / Long Short-Term Memory

M

Machine Learning (ML)Meta-learning Model Multi-head Attention Multimodal / Multimodality

N

Neural Network NLP / Natural Language Processing NLU / Natural Language Understanding Normalization Novelty Detection / Anomaly Detection

O

Objective Function One-hot Encoding Online Learning Optimizer Overfitting

P

Parameter Policy / Reinforcement Learning Policy Pooling Pretraining Prompt

Q

Q-learning Quality Estimation Quantization Query Queue / Buffer

R

Regularization Reinforcement Learning (RL)Representation Learning Retrieval Augmented Generation (RAG)RNN / Recurrent Neural Network

S

Sampling Self-Supervised Learning Sequence Modeling Softmax Supervised Learning

T

Tokenizer Training Data Transfer Learning Transformer Tuning / Hyperparameter Tuning

U

U-Net Uncertainty Estimation Underfitting Universal Approximation Theorem Unsupervised Learning

V

Validation Set Vanishing / Exploding Gradient Variational Autoencoder (VAE)Vector Embedding Vision Transformer (ViT)

W

Weak Supervision Weight Decay Whitening / Whitening Transformation Word Embedding Workflow

X

X-axis / feature axis XAI / Explainable AI XLM XLNet XOR problem

Y

Y-axis / feature axis Y-transform / YUV YAGNI (You Aren't Gonna Need It)Yield (model yield / throughput)Yoga of AI

Z

Z-score Normalization Zero-centric / Zero-bias initialization Zero-gradient phenomenon Zero-shot Learning / Zero-shot inference Zygosity in augmentation

What is U-Net

U-Net is a deep learning architecture designed for image segmentation, originally achieving remarkable success in the field of medical imaging. Its architecture is inspired by traditional convolutional neural networks (CNNs), featuring a symmetric encoder-decoder structure. Notably, U-Net integrates features from the encoder at each decoding step, significantly enhancing segmentation accuracy.

The importance of U-Net lies in its ability to maintain high performance with relatively few training samples, which is crucial in medical fields where data annotation is expensive and samples are scarce. Its operation involves extracting image features through successive convolution and pooling operations, and finally restoring the spatial resolution of the image via upsampling and convolution.

In practical applications, U-Net is widely utilized in various image segmentation tasks such as cell segmentation, medical image analysis, and remote sensing image processing. As deep learning technologies continue to evolve, many variants and improved versions of U-Net have emerged, such as Attention U-Net and 3D U-Net, to meet different application needs.

Looking ahead, U-Net and its variants are expected to play a significant role in handling high-dimensional data processing and complex scene segmentation. With stronger computing capabilities and richer datasets, the application scope of U-Net is anticipated to expand further.

Advantages include efficiency, the need for fewer training samples, and good segmentation accuracy, while disadvantages may include the need for additional improvements and adjustments for very complex images.

What is U-Net - Glossary