Barbara Caputo

Structured Domain Adaptation for 3D Keypoint Estimation

2019

Motivated by recent advances in deep domain adaptation, this paper introduces a deep architecture for estimating 3D keypoints when the training (source) and the test (target) images greatly differ in terms of visual appearance (domain …

Modeling Missing Annotations for Incremental Learning in Object Detection

2022 · arXiv (Cornell University)

Despite the recent advances in the field of object detection, common architectures are still ill-suited to incrementally detect new categories over time. They are vulnerable to catastrophic forgetting: they forget what has been already learned …