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

05/09/2022
by   Na Dong, et al.
0

Incremental few-shot object detection aims at detecting novel classes without forgetting knowledge of the base classes with only a few labeled training data from the novel classes. Most related prior works are on incremental object detection that rely on the availability of abundant training samples per novel class that substantially limits the scalability to real-world setting where novel data can be scarce. In this paper, we propose the Incremental-DETR that does incremental few-shot object detection via fine-tuning and self-supervised learning on the DETR object detector. To alleviate severe over-fitting with few novel class data, we first fine-tune the class-specific components of DETR with self-supervision from additional object proposals generated using Selective Search as pseudo labels. We further introduce a incremental few-shot fine-tuning strategy with knowledge distillation on the class-specific components of DETR to encourage the network in detecting novel classes without catastrophic forgetting. Extensive experiments conducted on standard incremental object detection and incremental few-shot object detection settings show that our approach significantly outperforms state-of-the-art methods by a large margin.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/10/2020

Incremental Few-Shot Object Detection

Most existing object detection methods rely on the availability of abund...
research
05/20/2021

Generalized Few-Shot Object Detection without Forgetting

Recently few-shot object detection is widely adopted to deal with data-l...
research
10/28/2021

Bridging Non Co-occurrence with Unlabeled In-the-wild Data for Incremental Object Detection

Deep networks have shown remarkable results in the task of object detect...
research
05/17/2021

Class-Incremental Few-Shot Object Detection

Conventional detection networks usually need abundant labeled training s...
research
08/19/2020

Towards Class-incremental Object Detection with Nearest Mean of Exemplars

Object detection has been widely used in the field of Internet, and deep...
research
09/01/2022

A New Knowledge Distillation Network for Incremental Few-Shot Surface Defect Detection

Surface defect detection is one of the most essential processes for indu...
research
02/01/2023

Towards Label-Efficient Incremental Learning: A Survey

The current dominant paradigm when building a machine learning model is ...

Please sign up or login with your details

Forgot password? Click here to reset