Where are the Blobs: Counting by Localization with Point Supervision

By Issam Hadj Laradji, Negar Rostamzadeh, Pedro H. O. Pinheiro, David Vázquez, Mark W. Schmidt. 2018

218 citations recorded by the source corpus.

Object counting is an important task in computer vision due to its growing demand in applications such as surveillance, traffic monitoring, and counting everyday objects. State-of-the-art methods use regression-based optimization where they explicitly learn to count the objects of interest. These often perform better than detection-based methods that need to learn the more difficult task of predicting the location, size, and shape of each object. However, we propose a detection-based method that does not need to estimate the size and shape of the objects and that outperforms regression-based methods. Our contributions are three-fold: (1) we propose a novel loss function that encourages the network to output a single blob per object instance using point-level annotations only; (2) we design two methods for splitting large predicted blobs between object instances; and (3) we show that our method achieves new state-of-the-art results on several challenging datasets including the Pascal VOC and the Penguins dataset. Our method even outperforms those that use stronger supervision such as depth features, multi-point annotations, and bounding-box labels.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Domain Adaptation for Traffic Density Estimation (2021, background): “Some relevant works present in the literature are (Ciampi et al., 2018), (Amato et al., 2019), (Amato et al., 2018), (Aich and Stavness, 2018), (Laradji et al., 2018).”
Pointly-Supervised Instance Segmentation (2021, background): “Point-based supervision has been studied in a variety of tasks, including action localization [37, 38], object detection [42, 46], object counting [27], and semantic segmentation [4, 44].”
MoVie: Revisiting Modulated Convolutions for Visual Counting and Beyond (2021, background): “Generalizing to multiple semantic classes and more instances, common object counting (Chattopadhyay et al., 2017) as a task has been explored with a variety of strategies such as detection (Ren et al., 2015), ensembling (Galton, 1907), or segmentation (Laradji et al., 2018).”
Guided Attention Network for Object Detection and Counting on Drones (2019, unknown): “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].”
Efficient Object Annotation via Speaking and Pointing (2019, background): “kind of labelling is efficient and provides useful supervision for several image (Papadopoulos et al. 2017b; Bearman et al. 2016; Laradji et al. 2018) and video”