Density map distillation for incremental object counting
C Wu, J van de Weijer - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
In this paper, we investigate the problem of incremental learning for object counting, where a
method must learn to count a variety of object classes from a sequence of datasets. A naive …
method must learn to count a variety of object classes from a sequence of datasets. A naive …
Learning to Count without Annotations
While recent supervised methods for reference-based object counting continue to improve
the performance on benchmark datasets they have to rely on small datasets due to the cost …
the performance on benchmark datasets they have to rely on small datasets due to the cost …
Training-free object counting with prompts
This paper tackles the problem of object counting in images. Existing approaches rely on
extensive training data with point annotations for each object, making data collection labor …
extensive training data with point annotations for each object, making data collection labor …
A unified object counting network with object occupation prior
S Jiang, Q Wang, F Cheng, Y Qi… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
The counting task, which plays a fundamental role in numerous applications (eg, crowd
counting, traffic statistics), aims to predict the number of objects with various densities …
counting, traffic statistics), aims to predict the number of objects with various densities …
TFCounter: Polishing Gems for Training-Free Object Counting
P Ting, J Lin, W Yu, W Zhang, X Chen, J Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
Object counting is a challenging task with broad application prospects in security
surveillance, traffic management, and disease diagnosis. Existing object counting methods …
surveillance, traffic management, and disease diagnosis. Existing object counting methods …
Learning to count anything: Reference-less class-agnostic counting with weak supervision
M Hobley, V Prisacariu - arXiv preprint arXiv:2205.10203, 2022 - arxiv.org
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 …
require reference images to define the type of object to be counted, as well as instance …
Adaptive dilated network with self-correction supervision for counting
The counting problem aims to estimate the number of objects in images. Due to large scale
variation and labeling deviations, it remains a challenging task. The static density map …
variation and labeling deviations, it remains a challenging task. The static density map …
Class-agnostic object counting robust to intraclass diversity
Most previous works on object counting are limited to pre-defined categories. In this paper,
we focus on class-agnostic counting, ie, counting object instances in an image by simply …
we focus on class-agnostic counting, ie, counting object instances in an image by simply …
Counting with adaptive auxiliary learning
This paper proposes an adaptive auxiliary task learning based approach for object counting
problems. Unlike existing auxiliary task learning based methods, we develop an attention …
problems. Unlike existing auxiliary task learning based methods, we develop an attention …
Object counting: You only need to look at one
This paper aims to tackle the challenging task of one-shot object counting. Given an image
containing novel, previously unseen category objects, the goal of the task is to count all …
containing novel, previously unseen category objects, the goal of the task is to count all …