DeepAI AI Chat
Log In Sign Up

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

by   Na Dong, et al.

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.


page 1

page 2

page 3

page 4


Incremental Few-Shot Object Detection

Most existing object detection methods rely on the availability of abund...

Generalized Few-Shot Object Detection without Forgetting

Recently few-shot object detection is widely adopted to deal with data-l...

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...

Class-Incremental Few-Shot Object Detection

Conventional detection networks usually need abundant labeled training s...

Towards Class-incremental Object Detection with Nearest Mean of Exemplars

Object detection has been widely used in the field of Internet, and deep...

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

Surface defect detection is one of the most essential processes for indu...

Demystifying the Base and Novel Performances for Few-shot Class-incremental Learning

Few-shot class-incremental learning (FSCIL) has addressed challenging re...