# Assisted Excitation of Activations: A Learning Technique to Improve Object Detectors

arXiv: https://arxiv.org/abs/1906.05388 · HTML: https://mlsanity.com/paper/1906.05388/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2019.

## Built on by (most cited first, 2 of 2)

- [PrObeD: Proactive Object Detection Wrapper](https://mlsanity.com/paper/2310.18788/) (2023)
- [Lightweight Delivery Detection on Doorbell Cameras](https://mlsanity.com/paper/2305.07812/) (2023)

## Abstract (arXiv)

We present a simple and effective learning technique that significantly improves mAP of YOLO object detectors without compromising their speed. During network training, we carefully feed in localization information. We excite certain activations in order to help the network learn to better localize. In the later stages of training, we gradually reduce our assisted excitation to zero. We reached a new state-of-the-art in the speed-accuracy trade-off. Our technique improves the mAP of YOLOv2 by 3.8% and mAP of YOLOv3 by 2.2% on MSCOCO dataset.This technique is inspired from curriculum learning. It is simple and effective and it is applicable to most single-stage object detectors.