Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector

Abstract

Conventional methods for object detection typically require a substantial amount of training data and preparing such high-quality training data is very labor-intensive. In this paper, we propose a novel few-shot object detection network that aims at detecting objects of unseen categories with only a few annotated examples. Central to our method are our Attention-RPN, Multi-Relation Detector and Contrastive Training strategy, which exploit the similarity between the few shot support set and query set to detect novel objects while suppressing false detection in the background. To train our network, we contribute a new dataset that contains 1000 categories of various objects with high-quality annotations. To the best of our knowledge, this is one of the first datasets specifically designed for few-shot object detection. Once our few-shot network is trained, it can detect objects of unseen categories without further training or fine-tuning. Our method is general and has a wide range of potential applications. We produce a new state-of-the-art performance on different datasets in the few-shot setting. The dataset link is https://github.com/fanq15/Few-Shot-Object-Detection-Dataset.

arXiv commentCVPR2020 Camera Ready. (Fix Figure 3 and Table 5. More implementation details in the supplementary material.)

References in corpus (11)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Prototypical Networks for Few-shot Learning
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
• Few-Example Object Detection with Model Communication
• Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
• LSTD: A Low-Shot Transfer Detector for Object Detection
• Low-Shot Learning from Imaginary Data
• RepMet: Representative-based metric learning for classification and one-shot object detection
• Memory Matching Networks for One-Shot Image Recognition
• Edge-labeling Graph Neural Network for Few-shot Learning

Cited by in corpus (3)

• One-Shot Object Detection without Fine-Tuning
• Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax
• A Few-Shot Sequential Approach for Object Counting