PNPDet : efficient few-shot detection without forgetting via Plug-and-Play sub-networks

The human visual system can detect objects of unseen categories from merely a few examples. However, such capability remains absent in state-of-the-art detectors. To bridge this gap, several attempts have been proposed to perform few-shot detection by incorporating meta-learning techniques. Such met...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhang, Gongjie, Cui, Kaiwen, Wu, Rongliang, Lu, Shijian, Tian, Yonghong
Other Authors: School of Electrical and Electronic Engineering
Format: Conference or Workshop Item
Language:English
Published: 2021
Subjects:
Online Access:https://hdl.handle.net/10356/146204
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:The human visual system can detect objects of unseen categories from merely a few examples. However, such capability remains absent in state-of-the-art detectors. To bridge this gap, several attempts have been proposed to perform few-shot detection by incorporating meta-learning techniques. Such methods can improve detection performance on unseen categories, but also add huge computational burden, and usually degrade detection performance on seen categories. In this paper, we present PNPDet, a novel Plug-and-Play Detector, for efficient few-shot detection without forgetting. It introduces a simple but effective architecture with separate sub-networks that disentangles the recognition of base and novel categories and prevents hurting performance on known categories while learning new concepts. Distance metric learning is further incorporated into sub-networks, consistently boosting detection performance for both base and novel categories. Experiments show that the proposed PNPDet can achieve comparable few-shot detection performance on unseen categories while not losing accuracy on seen categories, and also remain efficient and flexible at the same time.