Restoring Negative Information in Few-Shot Object Detection

by   Yukuan Yang, et al.

Few-shot learning has recently emerged as a new challenge in the deep learning field: unlike conventional methods that train the deep neural networks (DNNs) with a large number of labeled data, it asks for the generalization of DNNs on new classes with few annotated samples. Recent advances in few-shot learning mainly focus on image classification while in this paper we focus on object detection. The initial explorations in few-shot object detection tend to simulate a classification scenario by using the positive proposals in images with respect to certain object class while discarding the negative proposals of that class. Negatives, especially hard negatives, however, are essential to the embedding space learning in few-shot object detection. In this paper, we restore the negative information in few-shot object detection by introducing a new negative- and positive-representative based metric learning framework and a new inference scheme with negative and positive representatives. We build our work on a recent few-shot pipeline RepMet with several new modules to encode negative information for both training and testing. Extensive experiments on ImageNet-LOC and PASCAL VOC show our method substantially improves the state-of-the-art few-shot object detection solutions. Our code is available at


page 2

page 4

page 8

page 9


RepMet: Representative-based metric learning for classification and one-shot object detection

Distance metric learning (DML) has been successfully applied to object c...

Delving into the Imbalance of Positive Proposals in Two-stage Object Detection

Imbalance issue is a major yet unsolved bottleneck for the current objec...

Negative Margin Matters: Understanding Margin in Few-shot Classification

This paper introduces a negative margin loss to metric learning based fe...

Few-Shot Learning for Video Object Detection in a Transfer-Learning Scheme

Different from static images, videos contain additional temporal and spa...

Learning to Find Common Objects Across Image Collections

We address the problem of finding a set of images containing a common, b...

Segment-level Metric Learning for Few-shot Bioacoustic Event Detection

Few-shot bioacoustic event detection is a task that detects the occurren...

Multi-Scale Positive Sample Refinement for Few-Shot Object Detection

Few-shot object detection (FSOD) helps detectors adapt to unseen classes...

Please sign up or login with your details

Forgot password? Click here to reset