Completely Self-Supervised Crowd Counting via Distribution Matching
- URL: http://arxiv.org/abs/2009.06420v1
- Date: Mon, 14 Sep 2020 13:20:12 GMT
- Title: Completely Self-Supervised Crowd Counting via Distribution Matching
- Authors: Deepak Babu Sam, Abhinav Agarwalla, Jimmy Joseph, Vishwanath A.
Sindagi, R. Venkatesh Babu, Vishal M. Patel
- Abstract summary: We propose a complete self-supervision approach to training models for dense crowd counting.
The only input required to train, apart from a large set of unlabeled crowd images, is the approximate upper limit of the crowd count.
Our method dwells on the idea that natural crowds follow a power law distribution, which could be leveraged to yield error signals for backpropagation.
- Score: 92.09218454377395
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Dense crowd counting is a challenging task that demands millions of head
annotations for training models. Though existing self-supervised approaches
could learn good representations, they require some labeled data to map these
features to the end task of density estimation. We mitigate this issue with the
proposed paradigm of complete self-supervision, which does not need even a
single labeled image. The only input required to train, apart from a large set
of unlabeled crowd images, is the approximate upper limit of the crowd count
for the given dataset. Our method dwells on the idea that natural crowds follow
a power law distribution, which could be leveraged to yield error signals for
backpropagation. A density regressor is first pretrained with self-supervision
and then the distribution of predictions is matched to the prior by optimizing
Sinkhorn distance between the two. Experiments show that this results in
effective learning of crowd features and delivers significant counting
performance. Furthermore, we establish the superiority of our method in less
data setting as well. The code and models for our approach is available at
https://github.com/val-iisc/css-ccnn.
Related papers
- TokenUnify: Scalable Autoregressive Visual Pre-training with Mixture Token Prediction [61.295716741720284]
TokenUnify is a novel pretraining method that integrates random token prediction, next-token prediction, and next-all token prediction.
Cooperated with TokenUnify, we have assembled a large-scale electron microscopy (EM) image dataset with ultra-high resolution.
This dataset includes over 120 million annotated voxels, making it the largest neuron segmentation dataset to date.
arXiv Detail & Related papers (2024-05-27T05:45:51Z) - Robust Zero-Shot Crowd Counting and Localization With Adaptive Resolution SAM [55.93697196726016]
We propose a simple yet effective crowd counting method by utilizing the Segment-Everything-Everywhere Model (SEEM)
We show that SEEM's performance in dense crowd scenes is limited, primarily due to the omission of many persons in high-density areas.
Our proposed method achieves the best unsupervised performance in crowd counting, while also being comparable to some supervised methods.
arXiv Detail & Related papers (2024-02-27T13:55:17Z) - Semi-supervised Counting via Pixel-by-pixel Density Distribution
Modelling [135.66138766927716]
This paper focuses on semi-supervised crowd counting, where only a small portion of the training data are labeled.
We formulate the pixel-wise density value to regress as a probability distribution, instead of a single deterministic value.
Our method clearly outperforms the competitors by a large margin under various labeled ratio settings.
arXiv Detail & Related papers (2024-02-23T12:48:02Z) - Semi-Supervised Crowd Counting with Contextual Modeling: Facilitating Holistic Understanding of Crowd Scenes [19.987151025364067]
This paper presents a new semi-supervised method for training a reliable crowd counting model.
We foster the model's intrinsic'subitizing' capability, which allows it to accurately estimate the count in regions.
Our method achieves the state-of-the-art performance, surpassing previous approaches by a large margin on challenging benchmarks.
arXiv Detail & Related papers (2023-10-16T12:42:43Z) - CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model [60.30099369475092]
Supervised crowd counting relies heavily on costly manual labeling.
We propose a novel unsupervised framework for crowd counting, named CrowdCLIP.
CrowdCLIP achieves superior performance compared to previous unsupervised state-of-the-art counting methods.
arXiv Detail & Related papers (2023-04-09T12:56:54Z) - Wisdom of (Binned) Crowds: A Bayesian Stratification Paradigm for Crowd
Counting [16.09823718637455]
We analyze the performance of crowd counting approaches across standard datasets at per strata level and in aggregate.
Our contributions represent a nuanced, statistically balanced and fine-grained characterization of performance for crowd counting approaches.
arXiv Detail & Related papers (2021-08-19T16:50:31Z) - Active Crowd Counting with Limited Supervision [13.09054893296829]
We present an active learning framework which enables accurate crowd counting with limited supervision.
We first introduce an active labeling strategy to annotate the most informative images in the dataset and learn the counting model upon them.
In the last cycle when the labeling budget is met, the large amount of unlabeled data are also utilized.
arXiv Detail & Related papers (2020-07-13T12:07:25Z) - Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks [50.78037828213118]
This paper tackles the semi-supervised crowd counting problem from the perspective of feature learning.
We propose a novel semi-supervised crowd counting method which is built upon two innovative components.
arXiv Detail & Related papers (2020-07-07T05:30:53Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.