# Benchmark for Generic Product Detection: A Low Data Baseline for Dense Object Detection

arXiv: https://arxiv.org/abs/1912.09476 · HTML: https://mlsanity.com/paper/1912.09476/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2019.

## Built on by (most cited first, 3 of 3)

- [Semi-supervised Learning for Dense Object Detection in Retail Scenes](https://mlsanity.com/paper/2107.02114/) (2021)
- [Designing an Efficient End-to-end Machine Learning Pipeline for Real-time Empty-shelf Detection](https://mlsanity.com/paper/2205.13060/) (2022)
- [Machine Learning approaches to do size based reasoning on Retail Shelf objects to classify product variants](https://mlsanity.com/paper/2110.03783/) (2021)

## Abstract (arXiv)

Object detection in densely packed scenes is a new area where standard object detectors fail to train well. Dense object detectors like RetinaNet trained on large and dense datasets show great performance. We train a standard object detector on a small, normally packed dataset with data augmentation techniques. This dataset is 265 times smaller than the standard dataset, in terms of number of annotations. This low data baseline achieves satisfactory results (mAP=0.56) at standard IoU of 0.5. We also create a varied benchmark for generic SKU product detection by providing full annotations for multiple public datasets. It can be accessed at https://github.com/ParallelDots/generic-sku-detection-benchmark. We hope that this benchmark helps in building robust detectors that perform reliably across different settings in the wild.