# Learning to Count Objects with Few Exemplar Annotations

Source: [Learning to Count Objects with Few Exemplar Annotations](<https://www.sota2.com/research/paper/68fa65c61e209131cea0c6db>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:08:43.378Z

Authors: Jianfeng Wang, Rong Xiao, Yandong Guo, Lei Zhang

Published: 2019-05-20T06:28:44.000Z

## Abstract

In this paper, we study the problem of object counting with incomplete annotations. Based on the observation that in many object counting problems the target objects are normally repeated and highly similar to each other, we are particularly interested in the setting when only a few exemplar annotations are provided. Directly applying object detection with incomplete annotations will result in severe accuracy degradation due to its improper handling of unlabeled object instances. To address the problem, we propose a positiveness-focused object detector (PFOD) to progressively propagate the incomplete labels before applying the general object detection algorithm. The PFOD focuses on the positive samples and ignore the negative instances at most of the learning time. This strategy, though simple, dramatically boosts the object counting accuracy. On the CARPK dataset for parking lot car counting, we improved mAP@0.5 from 4.58% to 72.44% using only 5 training images each with 5 bounding boxes. On the Drink35 dataset for shelf product counting, the mAP@0.5 is improved from 14.16% to 53.73% using 10 training images each with 5 bounding boxes.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Car Object Counting on CARPK (test)](<https://www.sota2.com/research/sota/car-object-counting-on-carpk-test.md>): Car Object Counting; CARPK (test); MAE: 2.94.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1905.07898>)

[PDF](<https://arxiv.org/pdf/1905.07898.pdf>)
