SID: Incremental Learning for Anchor-Free Object Detection via Selective and Inter-Related Distillation

December 31, 2020 Β· Declared Dead Β· πŸ› Computer Vision and Image Understanding

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Can Peng, Kun Zhao, Sam Maksoud, Meng Li, Brian C. Lovell arXiv ID 2012.15439 Category cs.CV: Computer Vision Citations 58 Venue Computer Vision and Image Understanding Last Checked 5 months ago
Abstract
Incremental learning requires a model to continually learn new tasks from streaming data. However, traditional fine-tuning of a well-trained deep neural network on a new task will dramatically degrade performance on the old task -- a problem known as catastrophic forgetting. In this paper, we address this issue in the context of anchor-free object detection, which is a new trend in computer vision as it is simple, fast, and flexible. Simply adapting current incremental learning strategies fails on these anchor-free detectors due to lack of consideration of their specific model structures. To deal with the challenges of incremental learning on anchor-free object detectors, we propose a novel incremental learning paradigm called Selective and Inter-related Distillation (SID). In addition, a novel evaluation metric is proposed to better assess the performance of detectors under incremental learning conditions. By selective distilling at the proper locations and further transferring additional instance relation knowledge, our method demonstrates significant advantages on the benchmark datasets PASCAL VOC and COCO.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Computer Vision

πŸŒ… πŸŒ… Old Age

Fast R-CNN

Ross Girshick

cs.CV πŸ› ICCV πŸ“š 27.7K cites 11 years ago

Died the same way β€” πŸ‘» Ghosted