Active Learning for Object Detection with Non-Redundant Informative Sampling

TL;DR

This paper introduces NORIS, an active learning sampling method for object detection that combines uncertainty and diversity to select informative, non-redundant samples, reducing labeling costs significantly.

Contribution

The paper proposes NORIS, a novel active learning algorithm that measures collective information and uses object region features to improve sample diversity and informativeness.

Findings

Achieves 20% reduction in labeling cost on PASCAL-VOC

Achieves 30% reduction in labeling cost on KITTI

Outperforms state-of-the-art active learning baselines

Abstract

Curating an informative and representative dataset is essential for enhancing the performance of 2D object detectors. We present a novel active learning sampling strategy that addresses both the informativeness and diversity of the selections. Our strategy integrates uncertainty and diversity-based selection principles into a joint selection objective by measuring the collective information score of the selected samples. Specifically, our proposed NORIS algorithm quantifies the impact of training with a sample on the informativeness of other similar samples. By exclusively selecting samples that are simultaneously informative and distant from other highly informative samples, we effectively avoid redundancy while maintaining a high level of informativeness. Moreover, instead of utilizing whole image features to calculate distances between samples, we leverage features extracted from detected object regions within images to define object features. This allows us to construct a dataset encompassing diverse object types, shapes, and angles. Extensive experiments on object detection and image classification tasks demonstrate the effectiveness of our strategy over the state-of-the-art baselines. Specifically, our selection strategy achieves a 20% and 30% reduction in labeling costs compared to random selection for PASCAL-VOC and KITTI, respectively.