paper-with-me

홈 › Papers

CrowdMLP: Weakly-Supervised Crowd Counting via Multi-Granularity MLP

2022-03-15 · Mingjie Wang, Jun Zhou, Hao Cai, Minglun Gong

Existing state-of-the-art crowd counting algorithms rely excessively on location-level annotations, which are burdensome to acquire. When only count-level (weak) supervisory signals are available, it is arduous and error-prone to regress total counts due to the lack of explicit spatial constraints. To address this issue, a novel and efficient counter (referred to as CrowdMLP) is presented, which probes into modelling global dependencies of embeddings and regressing total counts by devising a multi-granularity MLP regressor. In specific, a locally-focused pre-trained frontend is cascaded to extract crude feature maps with intrinsic spatial cues, which prevent the model from collapsing into trivial outcomes. The crude embeddings, along with raw crowd scenes, are tokenized at different granularity levels. The multi-granularity MLP then proceeds to mix tokens at the dimensions of cardinality, channel, and spatial for mining global information. An effective proxy task, namely Split-Counting, is also proposed to evade the barrier of limited samples and the shortage of spatial hints in a self-supervised manner. Extensive experiments demonstrate that CrowdMLP significantly outperforms existing weakly-supervised counting algorithms and performs on par with state-of-the-art location-level supervised approaches.

📄 PDF Abstract BibTeX arXiv:2203.08219

Code (0)

등록된 구현이 없습니다.

Tasks

Crowd Counting

Similar Papers 제목 키워드 기반

WSCF-MVCC: Weakly-supervised Calibration-free Multi-view Crowd Counting

2025-12-02 · Bin Li, Daijie Chen, Qi Zhang arxiv

Multi-view crowd counting can effectively mitigate occlusion issues that commonly arise in single-image crowd counting. Existing deep-learning multi-view crowd counting methods project different camera view images onto a…

Crowd Counting

TransCrowd: weakly-supervised crowd counting with transformers

2021-04-19 · Dingkang Liang, Xiwu Chen, Wei Xu, Yu Zhou 외

The mainstream crowd counting methods usually utilize the convolution neural network (CNN) to regress a density map, requiring point-level annotations. However, annotating each person with a point is an expensive and lab…

Crowd Counting

Joint CNN and Transformer Network via weakly supervised Learning for efficient crowd counting

2022-03-12 · Fusen Wang, Kai Liu, Fei Long, Nong Sang 외

Currently, for crowd counting, the fully supervised methods via density map estimation are the mainstream research directions. However, such methods need location-level annotation of persons in an image, which is time-co…

Crowd CountingWeakly-supervised Learning

Weakly-Supervised Crowd Counting Learns from Sorting rather than Locations

2020-08-01 · ECCV 2020 8 · Yifan Yang, Guorong Li, Zhe Wu, Li Su 외

In crowd counting datasets, the location labels are costly, yet, they are not taken into the evaluation metrics. Besides, existing multi-task approaches employ high-level tasks to improve counting accuracy. This research…

Crowd Counting

Reinforcing Local Feature Representation for Weakly-Supervised Dense Crowd Counting

2022-02-22 · Xiaoshuang Chen, Hongtao Lu

Fully-supervised crowd counting is a laborious task due to the large amounts of annotations. Few works focus on weekly-supervised crowd counting, where only the global crowd numbers are available for training. The main c…

Crowd Counting