Continual Universal Object Detection
release_isdu63qks5bedgtxx2dpzt7o6e
by
Xialei Liu, Hao Yang, Avinash Ravichandran, Rahul Bhotika, Stefano
Soatto
2020
Abstract
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.
In text/plain
format
Archived Files and Locations
application/pdf 5.2 MB
file_kh6tbaik7nfgne7n6hwff265ua
|
arxiv.org (repository) web.archive.org (webarchive) |
2002.05347v1
access all versions, variants, and formats of this works (eg, pre-prints)