Towards Using Count-level Weak Supervision for Crowd Counting

@article{Lei2021TowardsUC,
  title={Towards Using Count-level Weak Supervision for Crowd Counting},
  author={Yinjie Lei and Yan Liu and Pingping Zhang and Lingqiao Liu},
  journal={Pattern Recognit.},
  year={2021},
  volume={109},
  pages={107616}
}
TransCrowd: Weakly-Supervised Crowd Counting with Transformer
TLDR
This paper proposes TransCrowd, which reformulates the weakly-supervised crowd counting problem from the perspective of sequence-to-count based on Transformer, and is the first work to adopt a pure Transformer for crowd counting research.
CrowdFormer: Weakly-supervised Crowd counting with Improved Generalizability
TLDR
A weaklysupervised method for crowd counting using a pyramid vision transformer that is comparable to the state-of-the-art on the benchmark crowd datasets and shows remarkable generalizability.
CrowdMLP: Weakly-Supervised Crowd Counting via Multi-Granularity MLP
TLDR
A novel and efficient counter that probes into modelling global dependencies of embeddings and regressing total counts by devising a multi-granularity MLP regressor and an effective proxy task, namely Split-Counting, is proposed to evade the barrier of limited samples and the shortage of spatial hints in a self-supervised manner.
Joint CNN and Transformer Network via weakly supervised Learning for efficient crowd counting
TLDR
A Joint CNN and Transformer Network (JCTNet) via weakly supervised learning for crowd counting is proposed and the phenomenon that a model constrained only by countlevel annotations can still focus on the crowd regions is explained.
Crowd Counting With Partial Annotations in an Image
TLDR
This paper studies a novel crowd counting setting, i.e. only using partial annotations in each image as training data, which achieves better performance than the recent methods and baselines under semi-supervised or active learning settings on all datasets.
Reinforcing Local Feature Representation for Weakly-Supervised Dense Crowd Counting
TLDR
This work proposes a self-adaptive feature similarity learning (SFSL) network and a global-local consistency (GLC) loss to reinforce local feature representation and introduces a feature vector which represents the unbiased feature estimation of persons.
Boosting Crowd Counting with Transformers
TLDR
A pure transformer is used to extract features with global information from overlapping image patches to predict the total person count of the image through regression-token module (RTM) and proposes a tokenattention module (TAM) to recalibrate encoded features through channel-wise attention informed by the context token.
Multi-level Convolutional Transformer with Adaptive Ranking for Semi-supervised Crowd Counting
TLDR
A semi-supervised crowd counting algorithm that is a mixture model of CNN and transformer that uses a region-level regression target for labeled images, which is a weaker regression approach than the location regression.
CCTrans: Simplifying and Improving Crowd Counting with Transformer
TLDR
This paper proposes a simple approach called CCTrans to simplify the design pipeline for crowd counting by utilizing 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, and an efficient regression head with multi-scale dilated convolution (MDC) to predict density maps.
Crowd Counting Using End-to-End Semantic Image Segmentation
TLDR
This paper proposed an end-to-end semantic segmentation framework for crowd counting in a dense crowded image based on semantic scene segmentation using an optimized convolutional neural network and successfully highlighted the foreground and suppressed the background part.
...
1
2
...

References

SHOWING 1-10 OF 85 REFERENCES
Bayesian Loss for Crowd Count Estimation With Point Supervision
TLDR
This work proposes Bayesian loss, a novel loss function which constructs a density contribution probability model from the point annotations, and outperforms previous best approaches by a large margin on the latest and largest UCF-QNRF dataset.
Context-Aware Crowd Counting
TLDR
This paper introduces an end-to-end trainable deep architecture that combines features obtained using multiple receptive field sizes and learns the importance of each such feature at each image location, which yields an algorithm that outperforms state-of-the-art crowd counting methods, especially when perspective effects are strong.
Almost Unsupervised Learning for Dense Crowd Counting
TLDR
Grid Winner-Take-All (GWTA) autoencoder is developed to learn several layers of useful filters from unlabeled crowd images to achieve superior results compared to other unsupervised methods and stays reasonably close to the accuracy of supervised baseline.
Towards Perspective-Free Object Counting with Deep Learning
TLDR
A novel convolutional neural network solution, named Counting CNN (CCNN), formulated as a regression model where the network learns how to map the appearance of the image patches to their corresponding object density maps, able to estimate object densities in different very crowded scenarios.
Gaussian Process Density Counting from Weak Supervision
TLDR
A weakly supervised kernel learner is devised that achieves higher count accuracies than previous counting models and imposes non-negativeness and smooth the GP response as an intermediary step in model inference.
Crowd Counting Using Multiple Local Features
TLDR
An approach that uses local features to count the number of people in each foreground blob segment, so that the total crowd estimate is the sum of the group sizes is proposed.
Mask-Aware Networks for Crowd Counting
TLDR
This work proposes to use a dedicated network branch to predict the object/non-object mask and then combine its prediction with the input image to produce the density map.
PaDNet: Pan-Density Crowd Counting
TLDR
The proposed Pan-Density Network (PaDNet) achieves state-of-the-art recognition performance and high robustness in pan-density crowd counting.
Feature-aware Adaptation and Structured Density Alignment for Crowd Counting in Video Surveillance
TLDR
This paper proposes a domain-adaptation-style crowd counting method, which can effectively adapt the model from synthetic data to the specific real-world scenes, and outperforms the state-of-the-art methods for the same cross-domain counting problem.
Fully Convolutional Crowd Counting on Highly Congested Scenes
TLDR
The state-of-the-art for crowd counting in high density scenes is advanced by further exploring the idea of a fully convolutional crowd counting model introduced by (Zhang et al., 2016), and a training set augmentation scheme that minimises redundancy among training samples to improve model generalisation and overall counting performance is developed.
...
1
2
3
4
5
...