Interactive Class-Agnostic Object Counting

by   Yifeng Huang, et al.

We propose a novel framework for interactive class-agnostic object counting, where a human user can interactively provide feedback to improve the accuracy of a counter. Our framework consists of two main components: a user-friendly visualizer to gather feedback and an efficient mechanism to incorporate it. In each iteration, we produce a density map to show the current prediction result, and we segment it into non-overlapping regions with an easily verifiable number of objects. The user can provide feedback by selecting a region with obvious counting errors and specifying the range for the estimated number of objects within it. To improve the counting result, we develop a novel adaptation loss to force the visual counter to output the predicted count within the user-specified range. For effective and efficient adaptation, we propose a refinement module that can be used with any density-based visual counter, and only the parameters in the refinement module will be updated during adaptation. Our experiments on two challenging class-agnostic object counting benchmarks, FSCD-LVIS and FSC-147, show that our method can reduce the mean absolute error of multiple state-of-the-art visual counters by roughly 30 user input. Our project can be found at


page 4

page 5

page 7

page 9

page 13

page 14

page 15

page 16


Exemplar Free Class Agnostic Counting

We tackle the task of Class Agnostic Counting, which aims to count objec...

ABC Easy as 123: A Blind Counter for Exemplar-Free Multi-Class Class-agnostic Counting

Class-agnostic counting methods enumerate objects of an arbitrary class,...

Iterative Correlation-based Feature Refinement for Few-shot Counting

Few-shot counting aims to count objects of any class in an image given o...

A Unified Object Counting Network with Object Occupation Prior

The counting task, which plays a fundamental rule in numerous applicatio...

SIMCO: SIMilarity-based object COunting

We present SIMCO, the first agnostic multi-class object counting approac...

Towards Partial Supervision for Generic Object Counting in Natural Scenes

Generic object counting in natural scenes is a challenging computer visi...

Towards Locally Consistent Object Counting with Constrained Multi-stage Convolutional Neural Networks

High-density object counting in surveillance scenes is challenging mainl...

Please sign up or login with your details

Forgot password? Click here to reset