# Foreground-Background Imbalance Problem in Deep Object Detectors: A Review

Source: [Foreground-Background Imbalance Problem in Deep Object Detectors: A Review](<https://www.sota2.com/research/paper/68fa67b51e209131cea17fd0>)

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

Data updated: 2025-10-25T22:21:05.859Z

Authors: Joya Chen, Qi Wu, Dong Liu, Tong Xu

Published: 2020-06-16T15:15:53.000Z

## Abstract

Recent years have witnessed the remarkable developments made by deep learning techniques for object detection, a fundamentally challenging problem of computer vision. Nevertheless, there are still difficulties in training accurate deep object detectors, one of which is owing to the foreground-background imbalance problem. In this paper, we survey the recent advances about the solutions to the imbalance problem. First, we analyze the characteristics of the imbalance problem in different kinds of deep detectors, including one-stage and two-stage ones. Second, we divide the existing solutions into two categories: sampling heuristics and non-sampling schemes, and review them in detail. Third, we experimentally compare the performance of some state-of-the-art solutions on the COCO benchmark. Promising directions for future work are also discussed.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2006.09238>)

[PDF](<https://arxiv.org/pdf/2006.09238.pdf>)