Active Learning for Deep Object Detection

TL;DR

This paper introduces a novel active learning approach for deep object detection that efficiently selects unlabeled samples to improve models, incorporating uncertainty metrics and class imbalance handling, evaluated on PASCAL VOC 2012.

Contribution

It proposes new uncertainty-based active learning metrics and an approach to handle class imbalance, enabling continuous exploration and incremental learning in object detection.

Findings

Effective sample selection improves detection performance

Class imbalance handling enhances learning efficiency

Method demonstrates continuous exploration on PASCAL VOC 2012

Abstract

The great success that deep models have achieved in the past is mainly owed to large amounts of labeled training data. However, the acquisition of labeled data for new tasks aside from existing benchmarks is both challenging and costly. Active learning can make the process of labeling new data more efficient by selecting unlabeled samples which, when labeled, are expected to improve the model the most. In this paper, we combine a novel method of active learning for object detection with an incremental learning scheme to enable continuous exploration of new unlabeled datasets. We propose a set of uncertainty-based active learning metrics suitable for most object detectors. Furthermore, we present an approach to leverage class imbalances during sample selection. All methods are evaluated systematically in a continuous exploration context on the PASCAL VOC 2012 dataset.