DeepAI AI Chat
Log In Sign Up

Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment

by   Guangxing Han, et al.
Columbia University

Few-shot object detection (FSOD) aims to detect objects using only few examples. It's critically needed for many practical applications but so far remains challenging. We propose a meta-learning based few-shot object detection method by transferring meta-knowledge learned from data-abundant base classes to data-scarce novel classes. Our method incorporates a coarse-to-fine approach into the proposal based object detection framework and integrates prototype based classifiers into both the proposal generation and classification stages. To improve proposal generation for few-shot novel classes, we propose to learn a lightweight matching network to measure the similarity between each spatial position in the query image feature map and spatially-pooled class features, instead of the traditional object/nonobject classifier, thus generating category-specific proposals and improving proposal recall for novel classes. To address the spatial misalignment between generated proposals and few-shot class examples, we propose a novel attentive feature alignment method, thus improving the performance of few-shot object detection. Meanwhile we jointly learn a Faster R-CNN detection head for base classes. Extensive experiments conducted on multiple FSOD benchmarks show our proposed approach achieves state of the art results under (incremental) few-shot learning settings.


page 1

page 2

page 3

page 5

page 7

page 14


Few-shot Object Detection via Feature Reweighting

This work aims to solve the challenging few-shot object detection proble...

Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networks

Few-shot object detection (FSOD) aims to detect never-seen objects using...

Meta R-CNN : Towards General Solver for Instance-level Low-shot Learning

Resembling the rapid learning capability of human, low-shot learning emp...

DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection

Few-shot object detection, which aims at detecting novel objects rapidly...

Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitation

Few-shot object detection has been extensively investigated by incorpora...

Hallucination Improves Few-Shot Object Detection

Learning to detect novel objects from few annotated examples is of great...

Few-Shot Video Object Detection

We introduce Few-Shot Video Object Detection (FSVOD) with three importan...