Related papers: Learning Error-Driven Curriculum for Crowd Countin…
Automatic estimation of the number of people in unconstrained crowded scenes is a challenging task and one major difficulty stems from the huge scale variation of people. In this paper, we propose a novel Deep Structured Scale Integration…
Crowd counting problem that counts the number of people in an image has been extensively studied in recent years. In this paper, we introduce a new variant of crowd counting problem, namely "Categorized Crowd Counting", that counts the…
In this work, we tackle the problem of crowd counting in images. We present a Convolutional Neural Network (CNN) based density estimation approach to solve this problem. Predicting a high resolution density map in one go is a challenging…
The order of training samples can have a significant impact on the performance of a classifier. Curriculum learning is a method of ordering training samples from easy to hard. This paper proposes the novel idea of a curriculum learning…
Datasets for training crowd counting deep networks are typically heavy-tailed in count distribution and exhibit discontinuities across the count range. As a result, the de facto statistical measures (MSE, MAE) exhibit large variance and…
With the increasing demand for large amount of labeled data, crowdsourcing has been used in many large-scale data mining applications. However, most existing works in crowdsourcing mainly focus on label inference and incentive design. In…
Tremendous variation in the scale of people/head size is a critical problem for crowd counting. To improve the scale invariance of feature representation, recent works extensively employ Convolutional Neural Networks with multi-column…
Traditional crowd counting networks suffer from information loss when feature maps are downsized through pooling layers, leading to inaccuracies in counting crowds at a distance. Existing methods often assume correct annotations during…
We focus on the problem of training a deep neural network in generations. The flowchart is that, in order to optimize the target network (student), another network (teacher) with the same architecture is first trained, and used to provide…
Localizing individuals in crowds is more in accordance with the practical demands of subsequent high-level crowd analysis tasks than simply counting. However, existing localization based methods relying on intermediate representations…
The problem of counting crowds in varying density scenes or in different density regions of the same scene, named as pan-density crowd counting, is highly challenging. Previous methods are designed for single density scenes or do not fully…
In supervised machine learning, use of correct labels is extremely important to ensure high accuracy. Unfortunately, most datasets contain corrupted labels. Machine learning models trained on such datasets do not generalize well. Thus,…
We propose a semi-supervised text classifier based on self-training using one positive and one negative property of neural networks. One of the weaknesses of self-training is the semantic drift problem, where noisy pseudo-labels accumulate…
We propose self-teaching networks to improve the generalization capacity of deep neural networks. The idea is to generate soft supervision labels using the output layer for training the lower layers of the network. During the network…
The Learning Rate (LR) has a high impact on deep learning training performance. A common practice is to train a Deep Neural Network (DNN) multiple times with different LR policies to find the optimal LR policy, which has been widely…
In this paper, we propose a novel SpatioTemporal convolutional Dense Network (STDNet) to address the video-based crowd counting problem, which contains the decomposition of 3D convolution and the 3D spatiotemporal dilated dense convolution…
Crowd image is arguably one of the most laborious data to annotate. In this paper, we devote to reduce the massive demand of densely labeled crowd data, and propose a novel weakly-supervised setting, in which we leverage the binary ranking…
A curriculum is a planned sequence of learning materials and an effective one can make learning efficient and effective for both humans and machines. Recent studies developed effective data-driven curriculum learning approaches for training…
Deep learning research over the past years has shown that by increasing the scope or difficulty of the learning problem over time, increasingly complex learning problems can be addressed. We study incremental learning in the context of…
Unsupervised crowd counting is a challenging yet not largely explored task. In this paper, we explore it in a transfer learning setting where we learn to detect and count persons in an unlabeled target set by transferring bi-knowledge…