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

03/15/2022
by   Mingjie Wang, et al.
0

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.

READ FULL TEXT

page 2

page 4

page 12

page 13

page 17

research
02/29/2020

Towards Using Count-level Weak Supervision for Crowd Counting

Most existing crowd counting methods require object location-level annot...
research
03/07/2022

CrowdFormer: Weakly-supervised Crowd counting with Improved Generalizability

Convolutional neural networks (CNNs) have dominated the field of compute...
research
04/19/2021

TransCrowd: Weakly-Supervised Crowd Counting with Transformer

The mainstream crowd counting methods usually utilize the convolution ne...
research
02/22/2022

Reinforcing Local Feature Representation for Weakly-Supervised Dense Crowd Counting

Fully-supervised crowd counting is a laborious task due to the large amo...
research
02/10/2023

GCNet: Probing Self-Similarity Learning for Generalized Counting Network

The class-agnostic counting (CAC) problem has caught increasing attentio...
research
07/08/2021

Crowd Counting via Perspective-Guided Fractional-Dilation Convolution

Crowd counting is critical for numerous video surveillance scenarios. On...
research
05/29/2022

Glance to Count: Learning to Rank with Anchors for Weakly-supervised Crowd Counting

Crowd image is arguably one of the most laborious data to annotate. In t...

Please sign up or login with your details

Forgot password? Click here to reset