Universal-Prototype Enhancing for Few-Shot Object Detection

TL;DR

This paper introduces a universal prototype framework to enhance feature generalization in few-shot object detection, improving performance on benchmarks by focusing on invariant object characteristics across categories.

Contribution

The paper proposes a universal prototype method that captures invariant features across categories and integrates a consistency loss to improve few-shot object detection.

Findings

Outperforms baseline by 6.8% mAP on VOC 1-shot Split2

Effective in enhancing feature invariance and generalization

Proven on PASCAL VOC and MS COCO datasets

Abstract

Few-shot object detection (FSOD) aims to strengthen the performance of novel object detection with few labeled samples. To alleviate the constraint of few samples, enhancing the generalization ability of learned features for novel objects plays a key role. Thus, the feature learning process of FSOD should focus more on intrinsical object characteristics, which are invariant under different visual changes and therefore are helpful for feature generalization. Unlike previous attempts of the meta-learning paradigm, in this paper, we explore how to enhance object features with intrinsical characteristics that are universal across different object categories. We propose a new prototype, namely universal prototype, that is learned from all object categories. Besides the advantage of characterizing invariant characteristics, the universal prototypes alleviate the impact of unbalanced object categories. After enhancing object features with the universal prototypes, we impose a consistency loss to maximize the agreement between the enhanced features and the original ones, which is beneficial for learning invariant object characteristics. Thus, we develop a new framework of few-shot object detection with universal prototypes ({FSOD}^{up}) that owns the merit of feature generalization towards novel objects. Experimental results on PASCAL VOC and MS COCO show the effectiveness of {FSOD}^{up}. Particularly, for the 1-shot case of VOC Split2, {FSOD}^{up} outperforms the baseline by 6.8% in terms of mAP.