Single Image Object Counting and Localizing Using Active-Learning

Inbar Huberman-Spiegelglas, Raanan Fattal; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022, pp. 1310-1319


The need to count and localize repeating objects in an image arises in different scenarios, such as biological microscopy studies, production-lines inspection, and surveillance recordings analysis. The use of supervised Convolutional Neural Networks (CNNs) achieves accurate object detection when trained over large class-specific datasets. The labeling effort in this approach does not pay-off when the counting is required over few images of a unique object class. We present a new method for counting and localizing repeating objects in single-image scenarios, assuming no pre-trained classifier is available. Our method trains a CNN over a small set of labels carefully collected from the input image in few active-learning iterations. At each iteration, the latent space of the network is analyzed to extract a minimal number of user-queries that strives to both sample the in-class manifold as thoroughly as possible as well as avoid redundant labels. Compared with existing user-assisted counting methods, our active-learning iterations achieve state-of-the-art performance in terms of counting and localizing accuracy, number of user mouse clicks, and running-time. This evaluation was performed through a large user study over a wide range of image classes with diverse conditions of illumination and occlusions.

Related Material

@InProceedings{Huberman-Spiegelglas_2022_WACV, author = {Huberman-Spiegelglas, Inbar and Fattal, Raanan}, title = {Single Image Object Counting and Localizing Using Active-Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2022}, pages = {1310-1319} }