Class-agnostic counting
<p>Nearly all existing counting methods are designed for a specific object class. Our work, however, aims to create a counting model able to count any class of object. To achieve this goal, we formulate counting as a matching problem, enabling us to exploit the image self-similarity property t...
Main Authors: | Lu, E, Xie, W, Zisserman, A |
---|---|
Format: | Conference item |
Published: |
Springer, Cham
2019
|
Similar Items
-
Learning to count anything: reference-less class-agnostic counting with weak supervision
by: Hobley, M, et al.
Published: (2023) -
Learning to count anything: reference-less class-agnostic counting with weak supervision
by: Hobley, M, et al.
Published: (2023) -
Attention-Assisted Feature Comparison and Feature Enhancement for Class-Agnostic Counting
by: Liang Dong, et al.
Published: (2023-11-01) -
ABC easy as 123: a blind counter for exemplar-free multi-class class-agnostic counting
by: Hobley, MA, et al.
Published: (2023) -
Cross Domain Adaptation of Crowd Counting with Model-Agnostic Meta-Learning
by: Xiaoyu Hou, et al.
Published: (2021-12-01)