Continual Universal Object Detection

02/13/2020
by   Xialei Liu, et al.
33

Object detection has improved significantly in recent years on multiple challenging benchmarks. However, most existing detectors are still domain-specific, where the models are trained and tested on a single domain. When adapting these detectors to new domains, they often suffer from catastrophic forgetting of previous knowledge. In this paper, we propose a continual object detector that can learn sequentially from different domains without forgetting. First, we explore learning the object detector continually in different scenarios across various domains and categories. Learning from the analysis, we propose attentive feature distillation leveraging both bottom-up and top-down attentions to mitigate forgetting. It takes advantage of attention to ignore the noisy background information and feature distillation to provide strong supervision. Finally, for the most challenging scenarios, we propose an adaptive exemplar sampling method to leverage exemplars from previous tasks for less forgetting effectively. The experimental results show the excellent performance of our proposed method in three different scenarios across seven different object detection datasets.

READ FULL TEXT

page 4

page 8

research
09/02/2020

Lifelong Object Detection

Recent advances in object detection have benefited significantly from ra...
research
09/28/2019

On Generalizing Detection Models for Unconstrained Environments

Object detection has seen tremendous progress in recent years. However, ...
research
04/09/2019

Towards Universal Object Detection by Domain Attention

Despite increasing efforts on universal representations for visual recog...
research
04/05/2022

Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation

Traditional object detectors are ill-equipped for incremental learning. ...
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
04/06/2023

Continual Detection Transformer for Incremental Object Detection

Incremental object detection (IOD) aims to train an object detector in p...
research
05/06/2022

Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning Benchmark for Lifelong Crowd Counting

Crowd Counting has important applications in public safety and pandemic ...

Please sign up or login with your details

Forgot password? Click here to reset