Boosting Crowd Counting via Multifaceted Attention

Lin, Hui; Ma, Zhenqiang; Ji, Rongrong; Wang, Yaowei; Xiao, Hong

doi:10.48550/arxiv.2203.02636

Cited by 3 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is good evidence that the dataset created and used in this paper is more suitable for real aquaculture scenarios and has more similar characteristics to the high-density characteristics of fish fry in such scenarios. Considering the actual culture conditions of fish fry crowding, this study draws on the idea of crowd density estimation in crowding scenarios [27][28][29] and marker methods from other similar studies [22]. In this study, for high-density, heavily obscured fry populations, the locations of the targets and the number of fish in the image were determined by marking the head of each fish.…”

Section: A Dataset 1) Dataset Acquisition and Annotationmentioning

confidence: 99%

Fry Counting Method in High-Density Culture Based on Image Enhancement Algorithm and Attention Mechanism

Chen,

Cheng,

Dou

et al. 2024

IEEE Access

View full text Add to dashboard Cite

It is important in production to achieve accurate counting and density estimation of highdensity culture fry under the environmental conditions of aquaculture scenarios in an efficient and accurate manner. However, none of the current methods for fry counting works well under the high-density and highoverlap conditions of real aquaculture scenarios. Therefore, in this paper, we propose a high-density farming fry monitoring network model, Super-Resolution GAN Density Estimate Attention Network (SGDAN), which incorporating an image enhancement algorithm and an attention mechanism, and we create a highdensity farming fry dataset (HD-FryDataset) based on the environmental conditions of real aquaculture scenarios. The network model is designed to improve and optimize the targeted subnetworks for several key aspects of high-density fish fry monitoring work. Four subnetworks are included for image optimization, feature extraction, attention, and density map estimation. The experimental results show that the SGDAN network model achieved an average counting accuracy of 97.57% on the high-density culture fry dataset, which was 8.23% and 2.06% higher than those of MCNN and CSRNet, respectively. Additionally, the MAE and RMSE of the model were reduced by 71.9% and 67.3% and by 34.3% and 33.2% compared with those of MCNN and CSRNet, respectively. The model proposed in this paper also has a better ability to generate predictive density maps. The density maps generated by SGDAN have values of the evaluation metrics PNSR and SSIM of 20.33 and 0.933, respectively, which are 3.31 and 0.037 and 2.63 and 0.031 higher than those of MCNN and CSRNet. In general, the network model proposed in this paper outperforms existing network models in two applications: accurate counting of fry and generation of density maps for high-density culture in aquaculture. It also provides a good solution for digitizing the number of fry and visualizing the density of high-density culture in intelligent aquaculture systems.

show abstract

Section: A Dataset 1) Dataset Acquisition and Annotationmentioning

confidence: 99%

Fry Counting Method in High-Density Culture Based on Image Enhancement Algorithm and Attention Mechanism

Chen,

Cheng,

Dou

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…i) Local feature aggregation: gene expression prediction can be considered as individually aggregating and identifying the feature of each gene type for the slide image window. The long-range dependency, i.e., global context, among identified features is needed to reason about complex scenarios [6,7], as those features are generally non-uniformly distributed across the slide image (see Sec. 3 for details).…”

Section: (C)mentioning

confidence: 99%

Spatial Transcriptomics Analysis of Gene Expression Prediction using Exemplar Guided Graph Neural Network

Yang¹,

Hossain

Stone³

et al. 2023

Preprint

View full text Add to dashboard Cite

Spatial transcriptomics (ST) is essential for understanding diseases and developing novel treatments. It measures the gene expression of each fine-grained area (i.e., different windows) in the tissue slide with low throughput. This paper proposes an exemplar guided graph network dubbed EGGN to accurately and efficiently predict gene expression from each window of a tissue slide image. We apply exemplar learning to dynamically boost gene expression prediction from nearest/similar exemplars of a given tissue slide image window. Our framework has three main components connected in a sequence: i) an extractor to structure a feature space for exemplar retrievals; ii) a graph construction strategy to connect windows and exemplars as a graph; iii) a graph convolutional network backbone to process window and exemplar features, and a graph exemplar bridging block to adaptively revise the window features using its exemplars. Finally, we complete the gene expression prediction task with a simple attention-based prediction block. Experiments on standard benchmark datasets indicate the superiority of our approach when compared with past state-of-the-art methods.

show abstract

“…Also, for the Low part, MSE surpasses the previous SOTA method by 27.58%, which is a great improvement. Unfortunately, however, in the Overall part, both metrics lag behind the MAN [46]. NWPU-Crowd is currently the most challenging dataset in the field of crowd counting.…”

Section: B Comparisons and Analysismentioning

confidence: 99%

Indirect-Instant Attention Optimization for Crowd Counting in Dense Scenes

Han¹,

Wang²,

Liu³

2022

Preprint

View full text Add to dashboard Cite

One of appealing approaches to guiding learnable parameter optimization, such as feature maps, is global attention, which enlightens network intelligence at a fraction of the cost. However, its loss calculation process still falls short: 1)We can only produce one-dimensional "pseudo labels" for attention, since the artificial threshold involved in the procedure is not robust;2) The attention awaiting loss calculation is necessarily highdimensional, and decreasing it by convolution will inevitably introduce additional learnable parameters, thus confusing the source of the loss. To this end, we devise a simple but efficient Indirect-Instant Attention Optimization (IIAO) module based on SoftMax-Attention , which transforms high-dimensional attention map into a one-dimensional feature map in the mathematical sense for loss calculation midway through the network, while automatically providing adaptive multi-scale fusion to feature pyramid module. The special transformation yields relatively coarse features and, originally, the predictive fallibility of regions varies by crowd density distribution, so we tailor the Regional Correlation Loss (RCLoss) to retrieve continuous error-prone regions and smooth spatial information . Extensive experiments have proven that our approach surpasses previous SOTA methods in many benchmark datasets. The code and pretrained models are publicly available in the manuscript submitted for review.

show abstract

Boosting Crowd Counting via Multifaceted Attention

Cited by 3 publications

References 29 publications

Fry Counting Method in High-Density Culture Based on Image Enhancement Algorithm and Attention Mechanism

Fry Counting Method in High-Density Culture Based on Image Enhancement Algorithm and Attention Mechanism

Spatial Transcriptomics Analysis of Gene Expression Prediction using Exemplar Guided Graph Neural Network

Indirect-Instant Attention Optimization for Crowd Counting in Dense Scenes

Contact Info

Product

Resources

About