Generalization to out-of-distribution (OOD) data is a capability natural to humans yet challenging for machines to reproduce. This is because most learning algorithms strongly …
Deep models, eg, CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in …
L Qiao, Y Zhao, Z Li, X Qiu, J Wu… - Proceedings of the …, 2021 - openaccess.thecvf.com
Few-shot object detection, which aims at detecting novel objects rapidly from extremely few annotated examples of previously unseen classes, has attracted significant research interest …
X Du, Z Wang, M Cai, Y Li - arXiv preprint arXiv:2202.01197, 2022 - arxiv.org
Out-of-distribution (OOD) detection has received much attention lately due to its importance in the safe deployment of neural networks. One of the key challenges is that models lack …
The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent years. Contrary to conventional approaches to AI where tasks are solved from scratch using …
G Zhang, Z Luo, Y Yu, K Cui… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Abstract The recently developed DEtection TRansformer (DETR) establishes a new object detection paradigm by eliminating a series of hand-crafted components. However, DETR …
Few-shot object detection has been extensively investigated by incorporating meta-learning into region-based detection frameworks. Despite its success, the said paradigm is still …
G Han, Y He, S Huang, J Ma… - Proceedings of the …, 2021 - openaccess.thecvf.com
Few-shot object detection (FSOD) aims to detect never-seen objects using few examples. This field sees recent improvement owing to the meta-learning techniques by learning how …
X Du, X Wang, G Gozum, Y Li - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Building reliable object detectors that can detect out-of-distribution (OOD) objects is critical yet underexplored. One of the key challenges is that models lack supervision signals from …