# S-OHEM: Stratified Online Hard Example Mining for Object Detection

## TL;DR

This paper introduces S-OHEM, a stratified sampling method for online hard example mining that improves object detection accuracy by considering loss distribution influences during training.

## Contribution

S-OHEM innovatively applies stratified sampling to hard example mining, enhancing detector performance and training efficiency over existing methods.

## Key findings

- Achieves 0.5% AP improvement on PASCAL VOC 2007 for rigid categories.
- Attains 1.6% AP increase on KITTI 2012 dataset.
- Provides a simple integration with existing detectors and regressors.

## Abstract

One of the major challenges in object detection is to propose detectors with highly accurate localization of objects. The online sampling of high-loss region proposals (hard examples) uses the multitask loss with equal weight settings across all loss types (e.g, classification and localization, rigid and non-rigid categories) and ignores the influence of different loss distributions throughout the training process, which we find essential to the training efficacy. In this paper, we present the Stratified Online Hard Example Mining (S-OHEM) algorithm for training higher efficiency and accuracy detectors. S-OHEM exploits OHEM with stratified sampling, a widely-adopted sampling technique, to choose the training examples according to this influence during hard example mining, and thus enhance the performance of object detectors. We show through systematic experiments that S-OHEM yields an average precision (AP) improvement of 0.5% on rigid categories of PASCAL VOC 2007 for both the IoU threshold of 0.6 and 0.7. For KITTI 2012, both results of the same metric are 1.6%. Regarding the mean average precision (mAP), a relative increase of 0.3% and 0.5% (1% and 0.5%) is observed for VOC07 (KITTI12) using the same set of IoU threshold. Also, S-OHEM is easy to integrate with existing region-based detectors and is capable of acting with post-recognition level regressors.