Deep learning approaches have recently raised the bar in many fields, from Natural
Language Processing to Computer Vision, by leveraging large amounts of data. However …

Humans are able to learn to recognize new objects even from a few examples. In contrast,
training deep-learning-based object detectors requires huge amounts of annotated data. To …

Few-shot object detection (FSOD), with the aim to detect novel objects using very few
training examples, has recently attracted great research interest in the community. Metric …

In the field of visual scene understanding, deep neural networks have made impressive
advancements in various core tasks like segmentation, tracking, and detection. However …

Recent self-supervised pretraining methods for object detection largely focus on pretraining
the backbone of the object detector, neglecting key parts of detection architecture. Instead …

Few-shot aerial image object detection aims to rapidly detect object instances of novel
category in aerial images by using few labeled samples. However, due to the complex …

Labeling data is often expensive and time-consuming, especially for tasks such as object
detection and instance segmentation, which require dense labeling of the image. While few …

We study the challenging incremental few-shot object detection (iFSD) setting. Recently,
hypernetwork-based approaches have been studied in the context of continuous and …

This paper proposes a methodology for building a robust instance segmentation model that
can effectively detect objects on construction sites under various weather conditions. We …

Under the domain shift, cross-domain few-shot object detection aims to adapt object
detectors in the target domain with a few annotated target data. There exists two significant …