Closing the Generalization Gap in One-Shot Object Detection

by   Claudio Michaelis, et al.

Despite substantial progress in object detection and few-shot learning, detecting objects based on a single example - one-shot object detection - remains a challenge: trained models exhibit a substantial generalization gap, where object categories used during training are detected much more reliably than novel ones. Here we show that this generalization gap can be nearly closed by increasing the number of object categories used during training. Our results show that the models switch from memorizing individual categories to learning object similarity over the category distribution, enabling strong generalization at test time. Importantly, in this regime standard methods to improve object detection models like stronger backbones or longer training schedules also benefit novel categories, which was not the case for smaller datasets like COCO. Our results suggest that the key to strong few-shot detection models may not lie in sophisticated metric learning approaches, but instead in scaling the number of categories. Future data annotation efforts should therefore focus on wider datasets and annotate a larger number of categories rather than gathering more images or instances per category.


page 2

page 4

page 7

page 10


Few-Shot Object Detection in Real Life: Case Study on Auto-Harvest

Confinement during COVID-19 has caused serious effects on agriculture al...

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

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

A Survey of Deep Learning for Low-Shot Object Detection

Object detection is a fundamental task in computer vision and image proc...

Few-Shot Object Detection: A Survey

Humans are able to learn to recognize new objects even from a few exampl...

Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions

A significant gap remains between today's visual pattern recognition mod...

Open Category Detection with PAC Guarantees

Open category detection is the problem of detecting "alien" test instanc...

Universal-Prototype Augmentation for Few-Shot Object Detection

Few-shot object detection (FSOD) aims to strengthen the performance of n...