Computer vision and multimodal learning · MLD-1147
Spatial padding
Values added around input boundaries to control how local operations handle edges and output size.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Preserve image dimensions through a convolution.
Original caveat
Spatial padding differs from adding padding tokens to sequences.
Context and aliases
Level: Intermediate. Stages: Architecture · Training · Inference.
Tags: DL · Vision · Multimodal.
Aliases: Padding.
Related concepts
Original references
- Learning Transferable Visual Models From Natural Language Supervision ↗ · Consulted
- Deep Learning: online textbook ↗ · Consulted
- PyTorch neural-network layers ↗ · Reference link
- Original reference URL ↗