Stanford Cars
A dataset containing 196 vehicle classes, each defined by a combination of make, model and year, with a hierarchical label structure. It is used to construct a fine-grained recognition benchmark with three levels of granularity: vehicle type, make and specific model.
Timeline (last 90 days)
The authors built a multi-granularity Stanford Cars benchmark covering three levels: vehicle type, brand, and specific model.
At the model granularity, SL-Ground raises AP from 14.5 for the token-level variant to 70.6 (under matched training candidate sampling conditions).
When trained with the full vocabulary, SL-Ground further reaches an AP of 86.0 at the model granularity.
The Stanford Cars dataset contains 196 vehicle categories, each defined by a 'brand—model—year' combination, and naturally possesses a hierarchical label structure.
All Facts (4)
The authors built a multi-granularity Stanford Cars benchmark covering three levels: vehicle type, brand, and specific model.
50%UnverifiedAt the model granularity, SL-Ground raises AP from 14.5 for the token-level variant to 70.6 (under matched training candidate sampling conditions).
50%UnverifiedWhen trained with the full vocabulary, SL-Ground further reaches an AP of 86.0 at the model granularity.
50%UnverifiedThe Stanford Cars dataset contains 196 vehicle categories, each defined by a 'brand—model—year' combination, and naturally possesses a hierarchical label structure.
50%