Class-Incremental Few-Shot Object Detection

05/17/2021
by   Pengyang Li, et al.
0

Conventional detection networks usually need abundant labeled training samples, while humans can learn new concepts incrementally with just a few examples. This paper focuses on a more challenging but realistic class-incremental few-shot object detection problem (iFSD). It aims to incrementally transfer the model for novel objects from only a few annotated samples without catastrophically forgetting the previously learned ones. To tackle this problem, we propose a novel method LEAST, which can transfer with Less forgetting, fEwer training resources, And Stronger Transfer capability. Specifically, we first present the transfer strategy to reduce unnecessary weight adaptation and improve the transfer capability for iFSD. On this basis, we then integrate the knowledge distillation technique using a less resource-consuming approach to alleviate forgetting and propose a novel clustering-based exemplar selection process to preserve more discriminative features previously learned. Being a generic and effective method, LEAST can largely improve the iFSD performance on various benchmarks.

READ FULL TEXT

page 1

page 3

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
10/12/2022

Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation

Class-incremental semantic segmentation (CISS) labels each pixel of an i...
research
04/23/2020

Few-Shot Class-Incremental Learning

The ability to incrementally learn new classes is crucial to the develop...
research
04/13/2023

Class-Incremental Learning of Plant and Disease Detection: Growing Branches with Knowledge Distillation

This paper investigates the problem of class-incremental object detectio...
research
03/16/2020

Context-Transformer: Tackling Object Confusion for Few-Shot Detection

Few-shot object detection is a challenging but realistic scenario, where...
research
07/17/2022

Learning with Recoverable Forgetting

Life-long learning aims at learning a sequence of tasks without forgetti...
research
03/27/2022

An Empirical Study and Comparison of Recent Few-Shot Object Detection Algorithms

The generic object detection (GOD) task has been successfully tackled by...

Please sign up or login with your details

Forgot password? Click here to reset