Multi-granularity sequence generation for hierarchical image classification

Multi-granularity sequence generation for hierarchical image classification

Abstract Hierarchical multi-granularity image classification is a challenging task that aims to tag each given image with multiple granularity labels simultaneously. Existing methods tend to overlook that different image regions contribute differently to label prediction at different granularities,...

Full beskrivning

Bibliografiska uppgifter
Huvudupphovsmän: Xinda Liu, Lili Wang
Materialtyp: Artikel
Språk:English
Publicerad: SpringerOpen 2024-01-01
Serie:Computational Visual Media
Ämnen:
hierarchical multi-granularity classification
vision and text transformer
sequence generation
fine-grained image recognition
cross-modality attention
Länkar:https://doi.org/10.1007/s41095-022-0332-2

Internet

https://doi.org/10.1007/s41095-022-0332-2

Liknande verk