FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding

TL;DR

This paper introduces FSCE, a contrastive proposal encoding method that improves few-shot object detection by enhancing feature embedding, leading to better classification of novel objects with minimal training data.

Contribution

The paper proposes a contrastive learning approach for FSOD that promotes intra-class compactness and inter-class separation of object proposals, outperforming existing methods.

Findings

Achieves up to +8.8% AP on PASCAL VOC

Outperforms state-of-the-art in all data splits and shots

Effective in reducing misclassification of rare objects

Abstract

Emerging interests have been brought to recognize previously unseen objects given very few training examples, known as few-shot object detection (FSOD). Recent researches demonstrate that good feature embedding is the key to reach favorable few-shot learning performance. We observe object proposals with different Intersection-of-Union (IoU) scores are analogous to the intra-image augmentation used in contrastive approaches. And we exploit this analogy and incorporate supervised contrastive learning to achieve more robust objects representations in FSOD. We present Few-Shot object detection via Contrastive proposals Encoding (FSCE), a simple yet effective approach to learning contrastive-aware object proposal encodings that facilitate the classification of detected objects. We notice the degradation of average precision (AP) for rare objects mainly comes from misclassifying novel instances as confusable classes. And we ease the misclassification issues by promoting instance level intra-class compactness and inter-class variance via our contrastive proposal encoding loss (CPE loss). Our design outperforms current state-of-the-art works in any shot and all data splits, with up to +8.8% on standard benchmark PASCAL VOC and +2.7% on challenging COCO benchmark. Code is available at: https: //github.com/MegviiDetection/FSCE