🏠 Home
Benchmark
📊 Tutti i benchmark 🦖 Dinosauro v1 🦖 Dinosauro v2 ✅ App To-Do List 🎨 Pagine libere creative 🎯 FSACB - Ultimate Showcase 🌍 Benchmark traduzione
Modelli
🏆 Top 10 modelli 🆓 Modelli gratuiti 📋 Tutti i modelli ⚙️ Kilo Code
Risorse
💬 Libreria di prompt 📖 Glossario IA 🔗 Link utili

Glossario IA

Il dizionario completo dell'Intelligenza Artificiale

162
categorie
2.032
sottocategorie
23.060
termini
📖
termini

Vision Transformer (ViT)

Neural architecture applying Transformer mechanisms to image processing by dividing images into sequences of patches for sequential processing.

📖
termini

Patch Embedding

Process of converting image patches into fixed-dimensional embedding vectors through linear projection to feed into the Transformer.

📖
termini

Class Token

Special token added to the embedding sequence whose final representation after passing through the Transformer is used for image classification.

📖
termini

Multi-Head Self-Attention

Mechanism allowing the model to simultaneously compute multiple attention representations to capture different relationships between image patches.

📖
termini

Transformer Encoder

Fundamental block composed of self-attention layers and feed-forward networks alternating with normalization and residual connections.

📖
termini

Image Patch Tokenization

Process of cutting an image into non-overlapping fixed-size patches, typically 16x16 pixels, which are then converted into sequential tokens.

📖
termini

Attention Map Visualization

Interpretability technique visualizing attention weights between patches to understand which image regions the model focuses on.

📖
termini

Pre-training on Large Datasets

Initial training phase on millions of images like ImageNet-21k to learn general visual representations before fine-tuning.

📖
termini

Patch Size Hyperparameter

Crucial parameter defining the dimension of image patches directly influencing computational complexity and model performance.

📖
termini

Token-to-Patch Reconstruction

Reverse process in generative tasks where tokens are converted back into image patches to reconstruct the original image.

📖
termini

Hierarchical Vision Transformer

Variant of ViT using a pyramid structure with variable patch sizes to capture multi-scale features.

📖
termini

Self-Supervised ViT Pre-training

Unsupervised training methods like DINO or MAE leveraging the Transformer structure to learn without annotations.

📖
termini

Cross-Attention in Multi-Modal ViT

Mechanism extending ViT to jointly process images and text using attention between different modalities.

📖
termini

Computational Complexity O(n²)

Quadratic complexity of self-attention with respect to the number of patches constituting the main limitation of Vision Transformers.

🔍

Nessun risultato trovato