paper-with-me

Papers

CCTrans: Simplifying and Improving Crowd Counting with Transformer

2021-09-29 · Ye Tian, Xiangxiang Chu, Hongpeng Wang

Most recent methods used for crowd counting are based on the convolutional neural network (CNN), which has a strong ability to extract local features. But CNN inherently fails in modeling the global context due to the limited receptive fields. However, the transformer can model the global context easily. In this paper, we propose a simple approach called CCTrans to simplify the design pipeline. Specifically, we utilize a pyramid vision transformer backbone to capture the global crowd information, a pyramid feature aggregation (PFA) model to combine low-level and high-level features, an efficient regression head with multi-scale dilated convolution (MDC) to predict density maps. Besides, we tailor the loss functions for our pipeline. Without bells and whistles, extensive experiments demonstrate that our method achieves new state-of-the-art results on several benchmarks both in weakly and fully-supervised crowd counting. Moreover, we currently rank No.1 on the leaderboard of NWPU-Crowd. Our code will be made available.

📄 PDF Abstract BibTeX arXiv:2109.14483

Code (2)

Nonad/Twins-with-RFB pytorch
wfs123456/CCTrans pytorch

Tasks

Crowd Counting

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Dilated Convolution 설명 없음
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

The Effectiveness of a Simplified Model Structure for Crowd Counting

2024-04-11 · Lei Chen, Xinghang Gao, Fei Chao, Xiang Chang 외

In the field of crowd counting research, many recent deep learning based methods have demonstrated robust capabilities for accurately estimating crowd sizes. However, the enhancement in their performance often arises fro…

Crowd CountingEfficient Neural Network

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

Locality-constrained Spatial Transformer Network for Video Crowd Counting

2019-07-18 · Yanyan Fang, Biyun Zhan, Wandi Cai, Shenghua Gao 외

Compared with single image based crowd counting, video provides the spatial-temporal information of the crowd that would help improve the robustness of crowd counting. But translation, rotation and scaling of people lead…

Crowd CountingTranslation

CrowdFormer: Weakly-supervised Crowd counting with Improved Generalizability

2022-03-07 · Siddharth Singh Savner, Vivek Kanhangad

Convolutional neural networks (CNNs) have dominated the field of computer vision for nearly a decade due to their strong ability to learn local features. However, due to their limited receptive field, CNNs fail to model …

Crowd Counting

Crowd Transformer Network

2019-04-04 · Viresh Ranjan, Mubarak Shah, Minh Hoai Nguyen

In this paper, we tackle the problem of Crowd Counting, and present a crowd density estimation based approach for obtaining the crowd count. Most of the existing crowd counting approaches rely on local features for estim…

Crowd CountingDensity Estimation