On Generalizing Detection Models for Unconstrained Environments
This work addresses generalization issues in object detection for unconstrained environments, such as autonomous driving, but is incremental as it builds on existing domain adaptation techniques.
The paper tackles the problem of object detection models failing to generalize across diverse data distributions by proposing an incremental learning approach with multiple domain-specific classifiers and transfer learning to avoid catastrophic forgetting, achieving effective results on the IDD and BDD100K datasets.
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.