Incremental Few-Shot Object Detection

03/10/2020
by   Juan-Manuel Pérez-Rúa, et al.
17

Most existing object detection methods rely on the availability of abundant labelled training samples per class and offline model training in a batch mode. These requirements substantially limit their scalability to open-ended accommodation of novel classes with limited labelled training data. terms of model accuracy and training efficiency during deployment. We present a study aiming to go beyond these limitations by considering the Incremental Few-Shot Detection (iFSD) problem setting, where new classes must be registered incrementally (without revisiting base classes) and with few examples. To this end we propose OpeN-ended Centre nEt (ONCE), a detector designed for incrementally learning to detect novel class objects with few examples. This is achieved by an elegant adaptation of the CentreNet detector to the few-shot learning scenario, and meta-learning a class-specific code generator model for registering novel classes. ONCE fully respects the incremental learning paradigm, with novel class registration requiring only a single forward pass of few-shot training samples, and no access to base classes – thus making it suitable for deployment on embedded devices. Extensive experiments conducted on both the standard object detection and fashion landmark detection tasks show the feasibility of iFSD for the first time, opening an interesting and very important line of research.

READ FULL TEXT

page 3

page 4

page 7

research
05/09/2022

Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning

Incremental few-shot object detection aims at detecting novel classes wi...
research
03/25/2022

Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detection

We study the challenging incremental few-shot object detection (iFSD) se...
research
08/18/2021

Few-Shot Batch Incremental Road Object Detection via Detector Fusion

Incremental few-shot learning has emerged as a new and challenging area ...
research
10/10/2021

Morphable Detector for Object Detection on Demand

Many emerging applications of intelligent robots need to explore and und...
research
05/06/2022

MINI: Mining Implicit Novel Instances for Few-Shot Object Detection

Learning from a few training samples is a desirable ability of an object...
research
05/29/2023

Few-shot Class-incremental Audio Classification Using Adaptively-refined Prototypes

New classes of sounds constantly emerge with a few samples, making it ch...
research
05/22/2014

Self-tuned Visual Subclass Learning with Shared Samples An Incremental Approach

Computer vision tasks are traditionally defined and evaluated using sema...

Please sign up or login with your details

Forgot password? Click here to reset