Few-Shot Learning for Road Object Detection
This work addresses the problem of detecting rare road objects for autonomous driving systems, but it is incremental as it evaluates existing methods on a new dataset.
The paper tackled few-shot object detection in real-world, class-imbalanced road scenarios using the India Driving Dataset, showing that a metric-learning method outperformed meta-learning by 11.2 mAP points on same-domain splits and 1.0 mAP point on open-set settings.
Few-shot learning is a problem of high interest in the evolution of deep learning. In this work, we consider the problem of few-shot object detection (FSOD) in a real-world, class-imbalanced scenario. For our experiments, we utilize the India Driving Dataset (IDD), as it includes a class of less-occurring road objects in the image dataset and hence provides a setup suitable for few-shot learning. We evaluate both metric-learning and meta-learning based FSOD methods, in two experimental settings: (i) representative (same-domain) splits from IDD, that evaluates the ability of a model to learn in the context of road images, and (ii) object classes with less-occurring object samples, similar to the open-set setting in real-world. From our experiments, we demonstrate that the metric-learning method outperforms meta-learning on the novel classes by (i) 11.2 mAP points on the same domain, and (ii) 1.0 mAP point on the open-set. We also show that our extension of object classes in a real-world open dataset offers a rich ground for few-shot learning studies.