Few-shot Object Detection via Feature Reweighting

Abstract

Conventional training of a deep CNN based object detector demands a large number of bounding box annotations, which may be unavailable for rare categories. In this work we develop a few-shot object detector that can learn to detect novel objects from only a few annotated examples. Our proposed model leverages fully labeled base classes and quickly adapts to novel classes, using a meta feature learner and a reweighting module within a one-stage detection architecture. The feature learner extracts meta features that are generalizable to detect novel object classes, using training data from base classes with sufficient samples. The reweighting module transforms a few support examples from the novel classes to a global vector that indicates the importance or relevance of meta features for detecting the corresponding objects. These two modules, together with a detection prediction module, are trained end-to-end based on an episodic few-shot learning scheme and a carefully designed loss function. Through extensive experiments we demonstrate that our model outperforms well-established baselines by a large margin for few-shot object detection, on multiple datasets and settings. We also present analysis on various aspects of our proposed model, aiming to provide some inspiration for future few-shot detection works.

arXiv commentICCV 2019

References in corpus (11)

• YOLOv3: An Incremental Improvement
• Prototypical Networks for Few-shot Learning
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• Fully Convolutional Networks for Semantic Segmentation
• Few-Example Object Detection with Model Communication
• Zero-Shot Detection
• Weakly-supervised Discovery of Visual Pattern Configurations
• Revisiting the Importance of Individual Units in CNNs via Ablation
• Distilling Critical Paths in Convolutional Neural Networks
• Low-Shot Learning with Imprinted Weights

Cited by in corpus (6)

• One-Shot Instance Segmentation
• Weakly-supervised Compositional FeatureAggregation for Few-shot Recognition
• Pixel and Feature Level Based Domain Adaption for Object Detection in Autonomous Driving
• Exploring Bottom-up and Top-down Cues with Attentive Learning for Webly Supervised Object Detection
• One of these (Few) Things is Not Like the Others
• Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning