Object counting method based on dual attention network

Zhang, Shihui; He, Li; Kong, Weihang

doi:10.1049/iet-ipr.2019.0465

Cited by 8 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The mall dataset is similar to UCSD, which contains single scene and a small number of pedestrians. On this dataset, this work gets the best result compared with [7, 8, 42, 43, 44]. It shows that MSR‐FAN has good generalization ability for general datasets.…”

Section: Methodsmentioning

confidence: 85%

“…The 1 × 1 convolution kernel can fuse the different channel features. To capture the feature-aware information hiding in the different channels, this paper defines the feature-aware feature as S O , which is shown as Equation (7).…”

Section: 3mentioning

confidence: 99%

“…The mapbased methods extract image features and do regression operation to generate the density map and get the number of people. Such approaches [7,8] can well overcome the crowd occlusion problem. However, the generalization ability of these models is poor.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

MSR‐FAN: Multi‐scale residual feature‐aware network for crowd counting

Zhao

Min

Wei

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

Crowd counting aims to count the number of people in crowded scenes, which is important to the security systems, traffic control and so on. The existing methods typically using local features cannot properly handle the perspective distortion and the varying scales in congested scene images, and henceforth perform wrong people counting. To alleviate this issue, this study proposes a multi-scale residual feature-aware network (MSR-FAN) that combines multi-scale features using multiple receptive field sizes and learns the featureaware information on each image. The MSR-FAN is trained end-to-end to generate highquality density map and evaluate the crowd number. The method consists of three parts. To handle the perspective changes problem, the first part, the direction-based featureenhanced network, is designed to encode the perspective information in four directions based on the initial image feature. The second part, the proposed multi-scale residual block module, gets the global information to handle the represent the regional feature better. This module explores features of different scales as well as reinforce the global feature. The third part, the feature-aware block, is designed to extract the feature hidden in the different channels. Experiment results based on benchmark datasets show that the proposed approach outperforms the existing state-of-the-art methods.

show abstract

Section: Methodsmentioning

confidence: 85%

Section: 3mentioning

confidence: 99%

See 1 more Smart Citation

MSR‐FAN: Multi‐scale residual feature‐aware network for crowd counting

Zhao

Min

Wei

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…An attention network has more power to extract layers and the important information contained inside the layers [39]. Shihui et al [40] reported on dual attention networks for object counting. This method was effective on pyramid structures and provided the spatial attention for processing multiscale features on a large scale, thus improving object counting performance.…”

Section: B Domain Adaptationmentioning

confidence: 99%

Domain Adaptation Deep Attention Network for Automatic Logo Detection and Recognition in Google Street View

et al. 2021

View full text Add to dashboard Cite

Signboards are important location landmarks that provide services to a local community. Nondisabled people can easily understand the meaning of a signboard based on its special shape; however, visually impaired people who need an assistive system to guide them to destinations or to help them understand their surroundings cannot. Currently, designing accurate assistive systems remain a challenge. Computer vision struggles to recognize signboards due to the diverse designs that combine text and images. Moreover, there is a lack of datasets to train the best model and reach good results. In this paper, we propose a novel framework that can automatically detect and recognize signboard logos. In addition, we utilize Google Street View to collect signboard images from Taiwan's streets. The proposed framework consists of a domain adaptation that not only reduces the loss function between source-target datasets, but also represents important source features adopted by the target dataset. In our model, we add nonlocal blocks and attention mechanisms called deep attention networks to achieve the best final result. We perform extensive experiments on both our dataset and public datasets to demonstrate the superior performance and effectiveness of our proposed method. The experimental results show that our proposed method outperforms state-of-the-art methods across all evaluation metrics.

show abstract

“…Image classification applications. From the view of applications, image classification has been used in various areas, such as retrieval [29], surveillance/monitoring [30,31] and medical analysis [32]. In these areas, researchers focus on natural images and specific-domain images related to traffic, remote sensing, industry, medical imaging and so forth.…”

Section: Related Workmentioning

confidence: 99%

Leveraging attention‐based visual clue extraction for image classification

Cui

Wang

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

Deep learning-based approaches have made considerable progress in image classification tasks, but most of the approaches lack interpretability, especially in revealing the decisive information causing the categorization of images. This paper seeks to answer the question of what clues encode the discriminative visual information between image categories and can help improve the classification performance. To this end, an attention-based clue extraction network (ACENet) is introduced to mine the decisive local visual information for image classification. ACENet constructs a clue-attention mechanism, that is globallocal attention, between the image and visual clue proposals extracted from it and then introduces a contrastive loss defined over the achieved discrete attention distribution to increase the discriminability of clue proposals. The loss encourages considerable attention to be devoted to discriminative clue proposals, that is those similar within the same category and dissimilar across categories. The experimental results for the Negative Web Image (NWI) dataset and the public ImageNet2012 dataset demonstrate that ACENet can extract true clues to improve the image classification performance and outperforms the baselines and the state-of-the-art methods.

show abstract

Object counting method based on dual attention network

Cited by 8 publications

References 23 publications

MSR‐FAN: Multi‐scale residual feature‐aware network for crowd counting

MSR‐FAN: Multi‐scale residual feature‐aware network for crowd counting

Domain Adaptation Deep Attention Network for Automatic Logo Detection and Recognition in Google Street View

Leveraging attention‐based visual clue extraction for image classification

Contact Info

Product

Resources

About