AI Glossary

Browse common vision AI and data intelligence terms to quickly understand key concepts.

2D to 3D Annotation
2D Bounding Box
3D Bounding Box Annotation
3D Annotation
3D Bounding Box
3D Reconstruction
Autonomous Checkout
Anchor-Free Detection
Anchor Box Principle
AR Virtual Fitting
Agricultural Pest and Disease Recognition
Auto-Orient (Automatic Orientation Correction/EXIF Repair)
API Key Management
Auto-Orient
Audio Event Temporal Annotation
Artificial Sound Classification Annotation
Action Classification Annotation
Axis-Aligned Bounding Box (AABB)
Annotation Validation
Annotation Testing
Annotation Evaluation
Annotation Optimization
Annotation Iteration
Annotation Version
Annotation Recovery
Annotation Backup
Annotation Desensitization
Annotation Encryption
Annotation Permission
Annotation Collaboration
Annotation Reusability
Annotation Interpretability
Annotation Traceability
Annotation Timeliness
Annotation Redundancy
Annotation Completeness
Annotation Ambiguity
Annotation Confidence
Annotation Weight
Annotation Dictionary
Annotation Mapping
Annotation Format
Annotation Output
Annotation Result
Annotation Record
Annotation Log
Annotation Relationship Library
Annotation Attribute Library
Annotation Label Library
Annotation Template
Annotation Cycle
Annotation Cost
Annotation Outsourcing
Annotation Service Provider
Annotation Team
Annotator
Assisted Annotation
Automatic annotation
Annotation Efficiency
Annotation Precision
Annotation Recall Rate
Annotation Accuracy Rate
Annotation Consistency
Annotation Correction
Annotation Verification
Annotation Review
Annotation Quality
Annotation Guide
Annotation Specification
Annotation Standard
Annotation Process
Annotation Project
Annotation Task
Annotated Sample
Annotated Dataset
Annotation Software
Annotation System
Annotation Platform
Annotation Tool
Attribute Annotation
Adversarial Examples
Attention Mechanism
Autonomous Driving Visual Perception
Amazon Rekognition
Azure Computer Vision
Affective Computing Agent
Agent-as-a-Service (AaaS)
AutoAgent
Agno
AutoGen
Azure AI Agents
Augmentation
AUC (Area Under the Curve)
Annotation Group
Annotation Format
Annotation
Anchor Box
Accuracy
Ablation Study
Assets
Artificial Intelligence (AI)
Anomaly Detection
Annotation
Anchor Boxes
Alphapose
AI Labeling
AI Assisted Labeling
AI (Artificial Intelligence)
AGI (Artificial General Intelligence)
Active Learning
Background Removal
Blur Augmentation
Base64 Image Encoding
Brightness Adjustment
BBox Jitter
Binarization
Background Noise Reduction Speech Transcription
Behavioral Relationship Annotation
Bbox-Polygon Conversion
Binary Mask
Bbox Splitting
Bbox Merging
Bbox Shrinkage
Bbox Expansion
Bbox Aspect Ratio
Bbox Depth
Bbox Height
Bbox Width
Bbox Center
Bbox IoU
Bbox Overlap
Bbox Regression
Bbox Annotation
Bbox Coordinate
Batch Annotation
Background Annotation
Bounding Box Annotation
Black Box
Batch Size
Batch Inference
Backpropagation
Bounding Box
Blur
Bias
Bidirectional Encoder Representation from Transformers (BERT)
BERT (Bidirectional Encoder Representation from Transformers)
Backbone
Consensus Algorithm
Content Moderation
Class Probability Prediction
Cutout
Cold Start
Containerized Deployment (Dockerizing)
COCO-Seg Format
CSV Annotation Format
CreateML JSON Format
COCO JSON Format
Cutout Augmentation
Copy-Paste Augmentation
CLAHE (Contrast Limited Adaptive Histogram Equalization)
Contrast Adjustment
Concept Prompts
Classification Annotation
Complex Polygon
Concave Polygon
Convex Polygon
Custom Format
COCO Format
Category Annotation
CountAnything
Custom Template
Canny Operator
CycleGAN
ChatGPT
Claude
Cross-Modal Agent
CrewAI
Copilot Studio
Cursor
CVAT (Computer Vision Annotation Tool)
Computer Vision Platform
Custom Head
Custom Dataset
Convolution
Convergence
Container
Confidence Threshold
Confidence
Classification
Class Balance
Checkpoint
Channel
Convolutional Neural Networks
Confusion Matrix
Concept Drift
Computer Vision Ontology
Computer Vision Model
Computer Vision
COCO
Classification
Class Imbalance
Class Boundary
ChatGPT
Chatbot
Calibration Curve
Data Lineage
Data-Centric AI
Data Silo
Data Slice
Data Curation
Document AI
Document OCR Recognition
Drone Image Analysis
Domain Adaptation
Dataset Versioning
Duplicate Images
Data Leakage
Dehazing
Denoising
Dangerous Audio Event Annotation
Dialect Speech Transcription
Domain Text Classification
Dynamic Target Annotation
Data Annotation
DINO-XSeek
DINO-X
DALL-E
Depth Estimation
Dynamic Memory Management
DataLoop
Domain Specific
Docker
Distributed
Differentiability
Deployment
Darknet
Dynamic and Event-based Classification
DICOM
Deep Learning
Decision Tree
Debug
Dataset
Data Types
Data Quality
Data Operations
Data Error
Data Drift
Data Augmentation
Data Approximation
Embedding Search
End-to-End object detection
Exposure Augmentation
Exposure Adjustment
EXIF Data Cleaning
Entity Relationship Extraction
Entity Type Annotation
Event Annotation
Emotion Annotation
Encord
ESRGAN (Enhanced Super-Resolution Generative Adversarial Network)
EfficientNet
Edge Agent
Environment
EMA
Edge Deployment
Early Stopping
Epoch
Embedding
Edge Detection
Filter Null
Feature Point Annotation
Frame Annotation
Foreground Annotation
Facial Expression Recognition
Facial Landmarks
Face Detection
Face Recognition
FPN (Feature Pyramid Network)
Faster R-CNN
Federated Learning-Enhanced Agent
Framework
FP16
FP8
Floating Point Operations Per Second
FLOPS
Forward Looking Infrared
FLIR
Filter Null
Feature Fusion
Feature
FastAI
Family
False Positive
False Negative
Frames Per Second (FPS)
Foundation Model
Fine-tuning
Few-Shot Learning
Feature
Feature Vector
Feature Extraction
False Positive Rate
F1 Score
Grid Cell
Gaussian Noise
Grayscale
Global Classification Annotation
Grounded SAM
Grounding DINO
Gaussian Filtering
Google Cloud Vision API
GRPO (Gradient-Based Reinforcement Learning for Agent Optimization)
Glean
Gradient
GPU Memory
GPU
Generalize
GAN Synthesis
Ground Truth
Greyscale
GPU (Graphical Processing Unit)
Ghost Frames
Generative Pre-Trained Transformer (GPT)
GAN (Generative Adversarial Network)
Hue/Saturation Jitter
Hosted Inference
HSV Shift
Horizontal Flip
Human Voice Classification Annotation
Hough Transform
Handwriting Recognition
HOG (Histogram of Oriented Gradients)
Hybrid Agent Architecture
Hosted Model
Hold-Out Set
Head
Hyperparameter
Human Pose Estimation
Human-in-the-Loop (HITL)
Image-based Product Search and Shopping
Inference Server
Inference API
ImageNet Format
Image Occlusion Simulation
Image Resizing
Image Preprocessing
Interactive Visual Segmentation
Image Exemplars
Instance Mask
Interactive Annotation
Image Caption Annotation
Image Retrieval Annotation
Image Classification Annotation
Image-Level Annotation
Instance Segmentation Annotation
Image Annotation
Image Retrieval
Infrared Vision
Image Captioning
Image Enhancement
Image Stitching
Image Registration
Industrial Defect Detection
ImageNet
Image Denoising
Image Generation
Image Classification
Intersection over Union (IoU)
Interpolation
Instance Segmentation
Inference
Imbalanced Dataset
Image Segmentation
Image Degradation
Image Annotation
JSON Response Parsing
Joint Point Annotation
JSON
Key Point Annotation
Keypoint Detection
Knowledge
K-Means Clustering
Keypoints
Label Consistency
Label Noise
License Plate Recognition (LPR)
Letterboxing
Latency
Lens Blur
Line Annotation
Loose Bounding Box
Label Annotation
Liveness Detection
Lane Detection
L4 Autonomous Agent
LangGraph
LabelU
LabelMe
LabelImg
Label Studio
Labelbox
Loss Function
Localization
Light Detection and Ranging
LiDAR
Layer
LLM (Large Language Models)
Lifecycle
Learning Rate
Label Error
Label
Metadata Filtering
Medical Image Analysis
Modify Classes
Model Endpoint
Multiclass Format
Motion Blur
Mixup Augmentation
Mosaic Augmentation
Memory-Based Video Tracker
Multi-Speaker Speech Transcription
Multimodal Annotation
Mask Contour
Mask Region
Mask Pixel
Mask IoU
Mask Accuracy
Mask Union
Mask Intersection
Mask Refinement
Mask Propagation
Mask Annotation
Manual Annotation
Median Filtering
Multi-Object Tracking (MOT)
Multimodal Fusion
Model Compression
Multi-Scale Feature Fusion
Medical Image Analysis
MMDetection
MobileNet
Mask R-CNN
Manus AI
Metaverse Agent
MCP (Model Context Protocol)
Multi-Agent Game Theory
Multi-Agent System (MAS)
MasterAgent
Makesense.ai
Mosaic
Model Zoo
Model Size
Mobile Deployment
Mixed Precision
Model-Assisted Labeling
Model Validation
Model Parameter
Model Accuracy
Model
MLOps (Machine Learning Operations)
Micro-Model
Metadata
Medical Image Segmentation
Mean Square Error (MSE)
Mean Average Precision (mAP)
Machine Learning
Natural Language Search
Normalization
Natural Sound Classification Annotation
Negative Sentiment Annotation
Named Entity Tag
Named Entity Recognition Annotation
Neural Style Transfer
Null Annotation
Non-Maximum Suppression
NMS
Neuron
Neural Architecture Search
Neck
Normalization
Noise
NLP (Natural Language Processing)
NIfTI
Neural Network
Nested Classification
Named Entity Recognition (NER)
One-Stage Detection Algorithm
Object Isolation
On-premise Deployment
Open Vocabulary Segmentation
OCR Text Annotation
Oriented Bounding Box (OBB)
Offline Annotation
Online Annotation
Object Detection Annotation
Object Annotation
Otsu's Algorithm
Optical Flow Estimation
OCR (Optical Character Recognition)
OpenAI
OpenCV (Open Source Computer Vision Library)
Outsourced Labeling
Output
OpenVINO
OpenCV
Open Neural Network Exchange
ONNX
Offline Prediction
Occlusion
Overfitting
Outlier Detection
Ontology
One-Shot Learning
Object Tracking
Object Localization
Object Detection
PPE Detection
Public Datasets
Pascal VOC XML Format
Padding
Presence Head
Promptable Concept Segmentation (PCS)
Part-of-Speech Sequence Annotation
Positive Sentiment Annotation
Point Cloud 3D Annotation
Polyline Annotation
Point Annotation
Polygon-Based Annotation
Polygonal Mask
Polygon Splitting
Polygon Merging
Polygon Clipping
Polygon Simplification
Polygon Approximation
Polygon Perimeter
Polygon Area
Polygon Coordinate
Polygon Contour
Polygon Edge
Polygon Vertex
Panoptic Segmentation Mask
Pre-Annotation
Pixel-Level Annotation
Panoptic Segmentation Annotation
Polygon Annotation
Point Cloud Segmentation
Person Re-identification (ReID)
Panorama
Point Cloud
Pixel
Pydantic AI
Playment
PixelAnnotationTool
PyTorch
Production
Pretrained Model
Preprocessing
Prediction
Polygon
Pipeline
Performance
Pascal VOC
PaddlePaddle
Preprocessing Algorithm
Precision
Pre-trained Model
Panoptic Segmentation
Quality Assurance (QA) in AI
QPS (Queries Per Second)
Quality Control (QC)
Query Synthesis Methods
Query Strategy
Retail Analytics
Retail Product Recognition
Random Flip
Remapping Class
Rate Limiting
Real-time Stream Inference (RTSP Inference)
Random Erasing
Random Crop
Random Shear
Random Rotation
Regional Classification Annotation
Road Marking Annotation
Relationship Extraction Annotation
Region-Level Annotation
Relationship Annotation
Remote Sensing Image Interpretation
ResNet (Residual Network)
Recursive Self-Evolution
Replit
RectLabel
Roboflow
Runtime Environment
Resolution
Requirements
Repo
Remap
Regularization
Region Attribute
Realtime
RasPi
Robotic Process Automation (RPA)
RLHF (Reinforcement Learning with Human Feedback)
Reinforcement Learning
Regression
Region-Based CNN
Recall
Random Forest
Satellite Imagery Analysis
Smart City AI
Smart Album Classification
Sports Action Analysis
Satellite Remote Sensing Analysis
Security Face Recognition
Source Images
Shear
Super Resolution
SDK Integration
Segmentation RLE Format
Salt and Pepper Noise
Sharpening
Static Crop
SA-Co benchmark (Segment Anything with Concepts benchmark)
Scalable Data Engine
Semantic Instance Segmentation
Segment Anything with Concepts
SAM 3
Speech Emotion Annotation
Syntactic Role Annotation
Semantic Relationship Annotation
Sentiment Intensity Annotation
Spatial Relationship Annotation
Scene Text Annotation
Sound Classification Annotation
Speech Transcription
Sequence Annotation
Sentiment Polarity Annotation
Simple Polygon
Semantic Mask
Semi-Automatic Annotation
Static Target Annotation
Scene Annotation
Skeleton Annotation
Semantic Segmentation Annotation
Stable Diffusion
Structure from Motion (SfM)
Stereo vision
Swin Transformer
Saliency Detection
Scene Text Detection
SLAM (Simultaneous Localization and Mapping)
Stereo Matching
Self-Supervised Learning
StyleGAN
SSD (Single Shot MultiBox Detector)
SURF (Speeded Up Robust Features)
SIFT (Scale-Invariant Feature Transform)
Super-Resolution Reconstruction
Self-Supervised Learning Agent
Swarm
StackBlitz
SuperAnnotate
Scale AI
Supervisely
Synthetic Data
Subjective
Subjective
SOTA
Single Shot Detector
SSD
Split
Self-Adversarial Training
Supervised Learning
Stream-based Selective Sampling
Segment Anything Model (SAM)
Scale Imbalance
Two-Stage Detection Algorithm
Traffic Vehicle Detection
Truncation
Throughput
TFRecord Format
Tiling
Target Temporal Tracking Annotation
Thematic Text Classification
Target Relationship Annotation
Temporal Bounding Box
Text Classification Annotation
Tight Bounding Box
Temporal Annotation
Target Annotation
Text Annotation
T-Rex Label
T-Rex2
Traffic Sign Recognition
Two Stage Detector
Tune
Train
Tradeoff
TPU
Tile
TFRecord
TensorFlow.js
TFJS
Test Set Bleed
TensorRT
TensorFlow Lite
TensorFlow
Tensorboard
Tensor Core
Tensor
Type 1 Errors
True Positive Rate (TPR)
Triplet Loss
Transformer
Transfer Learning
Training Data
Taxonomy
Ultralytics HUB
Ultralytics YOLO
UNet
Unsupervised Learning
Unstructured Data
Underfitting
Video Understanding
Visual Search
Vertical Flip
Vision Backbone
VOC Format
Video Annotation
Visual Question Answering (VQA)
Visual Odometry
ViT (Vision Transformer)
V7
VOTT (Visual Object Tagging Tool)
Version
Validate
Variance
Variable
Webhook Callback
Workflow
Weights
X-AnyLabeling
XML
YOLO Output Format Parsing
YOLO Grid Division Principle
YOLO Regression Problem Explanation
YOLO Object Detection Principle
YOLOv5 Ultralytics
YOLOv8 Ultralytics
YOLO11 Tracking
YOLO11 OBB Model
YOLO11 Pose Model
YOLO11 Segmentation Model
YOLO11 Detection Model
YOLO OBB Format
YOLO TXT Format
YOLO Format
Zero-Shot Learning