Single Image Object Counting and Localizing using Active-Learning
This addresses the need for efficient object counting in scenarios like microscopy or surveillance where labeling large datasets is impractical, though it is incremental as it builds on existing user-assisted methods.
The paper tackles the problem of counting and localizing repeating objects in single images without pre-trained classifiers by using an active-learning method that trains a CNN with minimal user queries. It achieves state-of-the-art performance in accuracy, user clicks, and running-time across diverse image classes.
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 Convoutional 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.