On Generalizing Detection Models for Unconstrained Environments

TL;DR

This paper proposes a domain adaptive incremental learning approach for object detection that improves generalization across diverse environments, especially under domain shifts, by using multiple classifiers and transfer learning.

Contribution

It introduces a novel domain adaptive incremental learning method with multiple classifiers to enhance detection model generalization in unconstrained environments.

Findings

Effective in reducing domain shift effects

Improves detection accuracy on IDD and BDD100K datasets

Avoids catastrophic forgetting in incremental learning

Abstract

Object detection has seen tremendous progress in recent years. However, current algorithms don't generalize well when tested on diverse data distributions. We address the problem of incremental learning in object detection on the India Driving Dataset (IDD). Our approach involves using multiple domain-specific classifiers and effective transfer learning techniques focussed on avoiding catastrophic forgetting. We evaluate our approach on the IDD and BDD100K dataset. Results show the effectiveness of our domain adaptive approach in the case of domain shifts in environments.