Dilated-Scale-Aware Category-Attention ConvNet for Multi-Class Object Counting

Xu, Wei; Liang, Dingkang; Zheng, Yixiao; Xie, Jiahao; Ma, Zhanyu

doi:10.1109/lsp.2021.3096119

Cited by 36 publications

(28 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Olmschenk [23] proposed a Semi-Supervised Dual-Goal Generative Adversarial Networks, which allows Dual-Goal GAN to benefit from unlabelled data during training and improves the prediction ability of the network. Xu et al [24] proposed an effective multi-task network based on a point-level annotation to achieve a multi-object counting task. The above methods all make a targeted network design for the scale variations.…”

Section: Crowd Countingmentioning

confidence: 99%

Domain adaptive crowd counting via dynamic scale aggregation network

Huo

Wang

Qiao

et al. 2023

IET Computer Vision

View full text Add to dashboard Cite

Crowd counting is an important research topic in computer vision. Its goal is to estimate the people's number in an image. Researchers have dramatically improved counting accuracy in recent years by regressing density maps. However, because of the inherent domain shift, the model trained on an expensive manually labelled dataset (source domain) does not perform well on a dataset with scarce labels (target domain). For this issue, a novel dynamic scale aggregation network (DSANet) is proposed to reduce the gaps in style and cross‐domain head scale variations. Specifically, a practical style transfer layer is introduced to reduce the appearance discrepancy between the source and target domains. Then, the translated source and target domain samples are encoded by a generator consisting of the VGG16 network and the dynamic scale aggregation modules (DSA Modules) and produce corresponding density maps. The DSA module can adaptively adjust parameters according to the input features and effectively fuse multi‐scale information to overcome the cross‐domain head scale variations. Next, a discriminator judges the input density map from the source or target domain. Last, domain distributions are aligned through adversarial between the generator and the discriminator. The experiments show that our network outperforms the current state‐of‐the‐art methods and can improve the target domain's performance while maintaining the source domain's performance without significant degradation.

show abstract

Section: Crowd Countingmentioning

confidence: 99%

Domain adaptive crowd counting via dynamic scale aggregation network

Huo

Wang

Qiao

et al. 2023

IET Computer Vision

View full text Add to dashboard Cite

show abstract

“…However, these localization-based methods usually report unsatisfactory counting performance. The mainstream of crowd counting is the density map CNN-based crowd counting methods [1,2,[24][25][26][27][28], whose integration of the density map gives the total count of a crowd image. Due to the commonly heavy occlusion that exists in crowd images, multi-scale architecture is developed.…”

Section: Cnn-based Crowd Countingmentioning

confidence: 99%

TransCrowd: weakly-supervised crowd counting with transformers

Liang

Chen

et al. 2022

Sci. China Inf. Sci.

Self Cite

148

View full text Add to dashboard Cite

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 laborious process. During the testing phase, the point-level annotations are not considered to evaluate the counting accuracy, which means the point-level annotations are redundant. Hence, it is desirable to develop weakly-supervised counting methods that just rely on count-level annotations, a more economical way of labeling. Current weakly-supervised counting methods adopt the CNN to regress a total count of the crowd by an image-to-count paradigm. However, having limited receptive fields for context modeling is an intrinsic limitation of these weakly-supervised CNN-based methods. These methods thus cannot achieve satisfactory performance, with limited applications in the real world. The transformer is a popular sequence-to-sequence prediction model in natural language processing (NLP), which contains a global receptive field. In this paper, we propose TransCrowd, which reformulates the weakly-supervised crowd counting problem from the perspective of sequence-to-count based on transformers. We observe that the proposed TransCrowd can effectively extract the semantic crowd information by using the self-attention mechanism of transformer. To the best of our knowledge, this is the first work to adopt a pure transformer for crowd counting research. Experiments on five benchmark datasets demonstrate that the proposed TransCrowd achieves superior performance compared with all the weakly-supervised CNN-based counting methods and gains highly competitive counting performance compared with some popular fully-supervised counting methods.

show abstract

“…Multi-scale architectures have played a significant role in many fields of computer vision [28,24,18,5,48,22,45,17], thanks to the multi-scale features and their cross-scale complementarity.…”

Section: Multi-scale Architecturesmentioning

confidence: 99%

Multi-Scale Adaptive Network for Single Image Denoising

Gou¹,

Hu²,

Lv³

et al. 2022

Preprint

View full text Add to dashboard Cite

Multi-scale architectures have shown effectiveness in a variety of tasks including single image denoising, thanks to appealing cross-scale complementarity. However, existing methods treat different scale features equally without considering their scale-specific characteristics, i.e., the within-scale characteristics are ignored. In this paper, we reveal this missing piece for multi-scale architecture design and accordingly propose a novel Multi-Scale Adaptive Network (MSANet) for single image denoising. To be specific, MSANet simultaneously embraces the withinscale characteristics and the cross-scale complementarity thanks to three novel neural blocks, i.e., adaptive feature block (AFeB), adaptive multi-scale block (AMB), and adaptive fusion block (AFuB). In brief, AFeB is designed to adaptively select details and filter noises, which is highly expected for fine-grained features. AMB could enlarge the receptive field and aggregate the multi-scale information, which is designed to satisfy the demands of both fine-and coarse-grained features. AFuB devotes to adaptively sampling and transferring the features from one scale to another scale, which is used to fuse the features with varying characteristics from coarse to fine. Extensive experiments on both three real and six synthetic noisy image datasets show the superiority of MSANet compared with 12 methods.

show abstract

Dilated-Scale-Aware Category-Attention ConvNet for Multi-Class Object Counting

Cited by 36 publications

References 34 publications

Domain adaptive crowd counting via dynamic scale aggregation network

Domain adaptive crowd counting via dynamic scale aggregation network

TransCrowd: weakly-supervised crowd counting with transformers

Multi-Scale Adaptive Network for Single Image Denoising

Contact Info

Product

Resources

About