DeepAI AI Chat
Log In Sign Up

Hallucination Improves Few-Shot Object Detection

by   Weilin Zhang, et al.

Learning to detect novel objects from few annotated examples is of great practical importance. A particularly challenging yet common regime occurs when there are extremely limited examples (less than three). One critical factor in improving few-shot detection is to address the lack of variation in training data. We propose to build a better model of variation for novel classes by transferring the shared within-class variation from base classes. To this end, we introduce a hallucinator network that learns to generate additional, useful training examples in the region of interest (RoI) feature space, and incorporate it into a modern object detection model. Our approach yields significant performance improvements on two state-of-the-art few-shot detectors with different proposal generation procedures. In particular, we achieve new state of the art in the extremely-few-shot regime on the challenging COCO benchmark.


page 1

page 2

page 3

page 4


Cooperating RPN's Improve Few-Shot Object Detection

Learning to detect an object in an image from very few training examples...

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

Few-shot object detection (FSOD) aims to detect objects using only few e...

Identification of Novel Classes for Improving Few-Shot Object Detection

Conventional training of deep neural networks requires a large number of...

Exploring Effective Knowledge Transfer for Few-shot Object Detection

Recently, few-shot object detection (FSOD) has received much attention f...

Generating Features with Increased Crop-related Diversity for Few-Shot Object Detection

Two-stage object detectors generate object proposals and classify them t...

Spatial Reasoning for Few-Shot Object Detection

Although modern object detectors rely heavily on a significant amount of...

Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection

Few-shot object detection is an imperative and long-lasting problem due ...