Leveraging Unlabeled Data for Crowd Counting by Learning to Rank

By Xialei Liu, Joost van de Weijer, Andrew D. Bagdanov. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018

307 citations recorded by the source corpus.

We propose a novel crowd counting approach that leverages abundantly available unlabeled crowd imagery in a learning-to-rank framework. To induce a ranking of cropped images, we use the observation that any sub-image of a crowded scene image is guaranteed to contain the same number or fewer persons than the super-image. This allows us to address the problem of limited size of existing datasets for crowd counting. We collect two crowd scene datasets from Google using keyword searches and query-by-example image retrieval, respectively. We demonstrate how to efficiently learn from these unlabeled datasets by incorporating learning-to-rank in a multi-task network which simultaneously ranks images and estimates crowd density maps. Experiments on two of the most challenging crowd counting datasets show that our approach obtains state-of-the-art results.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/5ece646d13786df1d84ff8eb2bfbc736dd337378

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning From Synthetic Data for Crowd Counting in the Wild (2019, methodology): “Mainstream CNN-based crowd counting methods [42, 43, 35, 36, 19, 22, 15, 7, 33, 26] yield the new record by designing the effective network architectures.”
Object Counting and Instance Segmentation With Image-Level Supervision (2019, background): “The problem of density map estimation to preserve the spatial distribution of people is well studied in crowd counting [3,16,18,22,32].”
JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method (2020, methodology): “Table 12 shows the results of the proposed method on ShanghaiTech as compared with several recent approaches: CP-CNN[6], IGCNN [30], D-ConvNet [33], Liu et al.[58], CSR-Net [75], icCNN [25], SA-Net[26], ACSCP [32] and Jian et al.[64], CANet [76], BCC [70], DSSI-Net [76], MBTTBF [63] and LSCCNN [69].”
Deep Learning for Anomaly Detection (2020, background): “osing a weak assumption of the ordinal order between anomaly and normal instances. (iii) This approach may build upon well-established ranking techniques and theories from areas like learning to rank [70,87,89]. Disadvantages. Their disadvantages are as follows. (i) At least some form of labeled ano”
Distribution Matching for Crowd Counting (2020, background): “Almost all prior crowd density map estimation methods [56, 57, 60, 38, 20, 33, 35, 4, 28, 50, 27, 40, 29, 26] have followed this convention.”
Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks (2019, methodology): “In scenes with severe occlusions and scale variations, CNN features are widely employed to enhance the feature encoding performance [52, 1, 26, 39, 2, 21].”
Guided Attention Network for Object Detection and Counting on Drones (2019, background): “Object counting methods aim to predict the total number of objects in different categories existing in images, such as pedestrian counting [20, 26, 46, 50], vehicle counting [12, 49], goods counting [11, 21] and general object counting [2, 3, 18].”
Context-Aware Crowd Counting (2018, background): “The regressors can be based on Random Forests [18], Gaussian Processes [7], or more recently Deep Nets [41, 42, 26, 31, 40, 36, 32, 24, 19, 30, 33, 22, 15, 28, 5], with most state-of-the-art approaches now relying on the latter.”
Attention Scaling for Crowd Counting (2020, methodology): “[21] proposed to incorporate self-supervised image ranking and density estimation into a multi-task learning framework, which makes it possible to learn from an abundant unlabeled crowd dataset.”