Losses and objectives · MLD-0887
Perceptual loss
A loss comparing learned feature representations rather than only raw pixels.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Improve visual similarity in image reconstruction.
Original caveat
Perceptual quality depends on the feature network.
Context and aliases
Level: Intermediate. Stages: Theory · Training · Evaluation.
Tags: ML · DL · SLM · LLM.
Aliases: None recorded.
Related concepts
Original references
- Deep Learning: online textbook ↗ · Consulted
- scikit-learn: evaluation metrics ↗ · Reference link
- PyTorch neural-network layers ↗ · Reference link
- Original reference URL ↗