A-Z of Machine Learning and Computer Vision Terms
A
AI Agent
AI Assistants
AI Assisted Labeling
Active Learning
Algorithm
Anchor Boxes
Anomaly Detection
Artificial Intelligence (AI)
Attribute
B
Backpropagation
Bagging
Batch
Batch Normalization
Bayesian Network
Bias
Big Data
Binary Classification
Blur
Boosting
Bounding Box
C
COCO
Calibration
Calibration Curve
Canonical Correlation Analysis (CCA)
Case-Based Reasoning
Chain of Thought (CoT)
ChatGPT
Chi-Squared Automatic Interaction Detection (CHAID)
Class Boundary (Statistics & Machine Learning)
Class Imbalance
Clustering
Collaborative Filtering
Computer Vision
Computer Vision Model
Concept Drift
Conditional Random Field (CRF)
Confusion Matrix
Constrained Clustering
Contrastive Learning
Convolutional Neural Networks (CNNs)
Cross-Validation
D
DICOM
Data Approximation
Data Augmentation
Data Drift
Data Error
Data Mining
Data Operations
Data Pre-processing
Data Quality
Dataset
Decision Boundary
Decision List
Decision Stump
Decision Tree
Deep Learning
Deep Neural Networks
Dimensionality Reduction
Dropout
Dynamic and Event-Based Classifications
E
Edge Cases
Edge Computing
Edge Detection
Elastic Net
Embedding Spaces
Ensemble Learning
Epoch
Expectation-Maximization Algorithm (EM)
Extreme Learning Machine
F
F1 Score
FP-Growth Algorithm
Factor Analysis
False Positive Rate
Feature
Feature Engineering
Feature Extraction
Feature Hashing
Feature Learning
Feature Scaling
Feature Selection
Feature Vector
Few-shot Learning
Fisher’s Linear Discriminant
Foundation Models
Frame Rate
Frames Per Second (FPS)
Fully Connected Layer
Fuzzy Logic
G
Generative Adversarial Network (GAN)
Generative Adversarial Networks
Generative Pre-Trained Transformer
Ghost Frames
Gradient Descent
Jaccard Index
The Jaccard Index, also known as Jaccard similarity coefficient, measures the similarity between two sets by dividing the size of their intersection by the size of their union. It’s defined as:
J(A, B) = |A ∩ B| / |A ∪ B|
Values range from 0 (no overlap) to 1 (identical sets). The Jaccard Index is commonly used in information retrieval, clustering evaluation, recommender systems, and computer vision tasks like semantic segmentation.
In classification, it’s useful for evaluating models on imbalanced data, particularly for multilabel tasks where traditional accuracy may be misleading. It’s also the basis for metrics like Intersection over Union (IoU) used in object detection.
Compared to cosine or Euclidean distance, the Jaccard Index focuses purely on set membership, ignoring frequency or magnitude. It works best for binary or categorical data and is often paired with Jaccard distance (1 - Jaccard Index) in clustering or similarity-based search.
Explore Our Products
Lightly One
Data Selection & Data Viewer
Get data insights and find the perfect selection strategy
Learn More
Lightly Train
Self-Supervised Pretraining
Leverage self-supervised learning to pretrain models
Learn More
Lightly Edge
Smart Data Capturing on Device
Find only the most valuable data directly on devide
Learn More