Learn new objects fast with few examples without forget old ones by hierarchical learning with HDA
Learn new objects fast with few examples without forget old ones by hierarchical learning with HDA
Fast Hierarchical Learning for Few-Shot Object Detection
arXiv paper abstract https://arxiv.org/abs/2210.05008v1
arXiv PDF paper https://arxiv.org/pdf/2210.05008v1.pdf
Transfer learning based approaches have recently achieved promising results on the few-shot detection task.
These approaches however suffer from ``catastrophic forgetting'' issue due to finetuning of base detector, leading to sub-optimal performance on the base classes.
Furthermore, the slow convergence rate of stochastic gradient descent (SGD) results in high latency and consequently restricts real-time applications.
... pose few-shot detection as a hierarchical learning problem, where the novel classes are treated as the child classes of existing base classes and the background class.
The detection heads for the novel classes are then trained using a specialized optimization strategy, leading to significantly lower training times compared to SGD.
... approach obtains competitive novel class performance on few-shot MS-COCO benchmark, while completely retaining the performance of the initial model on the base classes ...
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
#ComputerVision #ObjectDetection #AINewsClips #AI #ML #ArtificialIntelligence #MachineLearning
Comments