VIPriors Object Detection Challenge

TL;DR

This paper reports on a submission to the VIPriors Object Detection Challenge, highlighting data analysis, a new data augmentation method, and the use of softnms and model fusion to improve object detection from scratch.

Contribution

It introduces an effective data enhancement technique and demonstrates the benefits of softnms and model fusion for training object detectors from scratch.

Findings

Improved detection accuracy with data augmentation.

Enhanced performance through softnms and model fusion.

Successful training of models from scratch.

Abstract

This paper is a brief report to our submission to the VIPriors Object Detection Challenge. Object Detection has attracted many researchers' attention for its full application, but it is still a challenging task. In this paper, we study analysis the characteristics of the data, and an effective data enhancement method is proposed. We carefully choose the model which is more suitable for training from scratch. We benefit a lot from using softnms and model fusion skillfully.