Attention Guided Cosine Margin For Overcoming Class-Imbalance in Few-Shot Road Object Detection

TL;DR

This paper introduces Attention Guided Cosine Margin (AGCM), a novel method for few-shot object detection that improves class separation and reduces confusion, especially in imbalanced, real-world datasets.

Contribution

The paper proposes AGCM with Attentive Proposal Fusion and Cosine Margin Cross-Entropy loss to enhance feature clustering and class distinction in few-shot object detection.

Findings

Outperforms state-of-the-art on IDD dataset by up to 6.4 mAP points.

Achieves up to 4.9 mAP points improvement on PASCAL-VOC.

Effectively reduces catastrophic forgetting and class confusion.

Abstract

Few-shot object detection (FSOD) localizes and classifies objects in an image given only a few data samples. Recent trends in FSOD research show the adoption of metric and meta-learning techniques, which are prone to catastrophic forgetting and class confusion. To overcome these pitfalls in metric learning based FSOD techniques, we introduce Attention Guided Cosine Margin (AGCM) that facilitates the creation of tighter and well separated class-specific feature clusters in the classification head of the object detector. Our novel Attentive Proposal Fusion (APF) module minimizes catastrophic forgetting by reducing the intra-class variance among co-occurring classes. At the same time, the proposed Cosine Margin Cross-Entropy loss increases the angular margin between confusing classes to overcome the challenge of class confusion between already learned (base) and newly added (novel) classes. We conduct our experiments on the challenging India Driving Dataset (IDD), which presents a real-world class-imbalanced setting alongside popular FSOD benchmark PASCAL-VOC. Our method outperforms State-of-the-Art (SoTA) approaches by up to 6.4 mAP points on the IDD-OS and up to 2.0 mAP points on the IDD-10 splits for the 10-shot setting. On the PASCAL-VOC dataset, we outperform existing SoTA approaches by up to 4.9 mAP points.