Open-world Text-specified Object Counting

TL;DR

This paper introduces CounTX, a transformer-based model for open-world object counting using text descriptions, outperforming previous methods on the FSC-147 benchmark and providing an enhanced dataset with detailed class descriptions.

Contribution

We propose CounTX, a novel class-agnostic, end-to-end model for text-specified object counting, and release an improved dataset FSC-147-D with detailed descriptions.

Findings

CounTX exceeds state-of-the-art on FSC-147 benchmark.

FSC-147-D enables more detailed object class descriptions.

The model is trained end-to-end with joint text-image representations.

Abstract

Our objective is open-world object counting in images, where the target object class is specified by a text description. To this end, we propose CounTX, a class-agnostic, single-stage model using a transformer decoder counting head on top of pre-trained joint text-image representations. CounTX is able to count the number of instances of any class given only an image and a text description of the target object class, and can be trained end-to-end. In addition to this model, we make the following contributions: (i) we compare the performance of CounTX to prior work on open-world object counting, and show that our approach exceeds the state of the art on all measures on the FSC-147 benchmark for methods that use text to specify the task; (ii) we present and release FSC-147-D, an enhanced version of FSC-147 with text descriptions, so that object classes can be described with more detailed language than their simple class names. FSC-147-D and the code are available at https://www.robots.ox.ac.uk/~vgg/research/countx.