Abstract: Object detection is a fundamental computer vision task that simultaneously locates and categorizes objects in images and videos. It is utilized in various fields, such as autonomous driving, ...
We introduce a Hybrid Ensemble Decoder (HED) to improve query diversity and model robustness. We propose a simple fine-tuning recipe for cross-domain few-shot object detection, with plateau-aware ...
Turn Excel into a lightweight data-science tool for cleaning datasets, standardizing dates, visualizing clusters, and analyzing keywords.
Abstract: Source-Free Object Detection (SFOD) enables knowledge transfer from a source domain to an unsupervised target domain for object detection without access to source data. Most existing SFOD ...