Meta Guided Metric Learner for Overcoming Class Confusion in Few-Shot Road Object Detection

TL;DR

This paper introduces a Meta Guided Metric Learner (MGML) that improves few-shot road object detection by reducing class confusion and enhancing discriminative features, significantly outperforming existing methods on multiple datasets.

Contribution

The paper proposes a novel MGML approach with a Squeeze and Excite module and Orthogonality Constraint to address class confusion in FSOD, achieving state-of-the-art results.

Findings

Outperforms SOTA on India Driving Dataset by up to 11 mAP points

Achieves only 20% class confusion with 10 examples per class

Surpasses SOTA on PASCAL VOC few-shot splits by up to 5.8 mAP

Abstract

Localization and recognition of less-occurring road objects have been a challenge in autonomous driving applications due to the scarcity of data samples. Few-Shot Object Detection techniques extend the knowledge from existing base object classes to learn novel road objects given few training examples. Popular techniques in FSOD adopt either meta or metric learning techniques which are prone to class confusion and base class forgetting. In this work, we introduce a novel Meta Guided Metric Learner (MGML) to overcome class confusion in FSOD. We re-weight the features of the novel classes higher than the base classes through a novel Squeeze and Excite module and encourage the learning of truly discriminative class-specific features by applying an Orthogonality Constraint to the meta learner. Our method outperforms State-of-the-Art (SoTA) approaches in FSOD on the India Driving Dataset (IDD) by upto 11 mAP points while suffering from the least class confusion of 20% given only 10 examples of each novel road object. We further show similar improvements on the few-shot splits of PASCAL VOC dataset where we outperform SoTA approaches by upto 5.8 mAP accross all splits.