Journal
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Volume 44, Issue 12, Pages 9209-9216Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2021.3124133
Keywords
Task analysis; Detectors; Object detection; Training; Proposals; Standards; Feature extraction; Object detection; incremental learning; deep neural networks; meta-learning; gradient preconditioning
Funding
- DST through the IMPRINT program [IMP/2019/000250]
- TCS PhD Fellowship
- VR [2016-05543]
- Swedish Research Council [2016-05543] Funding Source: Swedish Research Council
Ask authors/readers for more resources
In this study, a meta-learning approach is proposed to achieve incremental learning by learning how to reshape model gradients. Compared to existing methods, this approach can adapt to new tasks and performs well in various incremental learning scenarios.
In a real-world setting, object instances from new classes can be continuously encountered by object detectors. When existing object detectors are applied to such scenarios, their performance on old classes deteriorates significantly. A few efforts have been reported to address this limitation, all of which apply variants of knowledge distillation to avoid catastrophic forgetting. We note that although distillation helps to retain previous learning, it obstructs fast adaptability to new tasks, which is a critical requirement for incremental learning. In this pursuit, we propose a meta-learning approach that learns to reshape model gradients, such that information across incremental tasks is optimally shared. This ensures a seamless information transfer via a meta-learned gradient preconditioning that minimizes forgetting and maximizes knowledge transfer. In comparison to existing meta-learning methods, our approach is task-agnostic, allows incremental addition of new-classes and scales to high-capacity models for object detection. We evaluate our approach on a variety of incremental learning settings defined on PASCAL-VOC and MS COCO datasets, where our approach performs favourably well against state-of-the-art methods. Code and trained models: https://github.com/JosephKJ/iOD.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available