Learning to count anything: reference-less class-agnostic counting with weak supervision
Current class-agnostic counting methods can generalise to unseen classes but usually require reference images to define the type of object to be counted, as well as instance annotations during training. Reference-less class-agnostic counting is an emerging field that identifies counting as, at its c...
Hlavní autoři: | Hobley, M, Prisacariu, V |
---|---|
Médium: | Conference item |
Jazyk: | English |
Vydáno: |
2023
|
Podobné jednotky
-
Learning to count anything: reference-less class-agnostic counting with weak supervision
Autor: Hobley, M, a další
Vydáno: (2023) -
ABC easy as 123: a blind counter for exemplar-free multi-class class-agnostic counting
Autor: Hobley, MA, a další
Vydáno: (2023) -
Class-agnostic counting
Autor: Lu, E, a další
Vydáno: (2019) -
Counting with limited supervision
Autor: Hobley, MA
Vydáno: (2023) -
DMS: differentiable mean shift for dataset agnostic task specific clustering using side information
Autor: Hobley, M, a další
Vydáno: (2023)