Feature Map
/ˈfiːtʃər mæp/
Feature Map: The output of applying a convolution filter to an input, representing detected features. Each filter produces one feature map showing where specific features (edges, textures, patterns) are detected. Multiple filters produce multiple feature maps, each capturing different aspects of the input.
In italiano: Feature MapLegge I · Embedding, feature e spazi vettorialiEach filter produces one feature map showing where specific features (edges, textures, patterns) are detected. Multiple filters produce multiple feature maps, each capturing different aspects of the input.
Examples
- Edge detection feature map
- Texture feature maps
- High-level semantic features