timy90022/One-Shot-Object-Detection
A PyTorch implementation of a one-shot object detection model using co-attention and co-excitation mechanisms, based on a NeurIPS 2019 paper.
Not currently ranked — collecting fresh signals.
star history
Implements a one-shot object detection approach that uses co-attention and co-excitation mechanisms to detect novel objects from a single reference example. The implementation builds on Faster R-CNN architecture with a ResNet50 backbone pretrained on ImageNet (excluding COCO-overlapping classes). The model supports training and evaluation on COCO dataset.
Frequently asked
- What is timy90022/One-Shot-Object-Detection?
- A PyTorch implementation of a one-shot object detection model using co-attention and co-excitation mechanisms, based on a NeurIPS 2019 paper.
- Is One-Shot-Object-Detection open source?
- Yes — timy90022/One-Shot-Object-Detection is open source, released under the MIT license.
- What language is One-Shot-Object-Detection written in?
- timy90022/One-Shot-Object-Detection is primarily written in Python.
- How popular is One-Shot-Object-Detection?
- timy90022/One-Shot-Object-Detection has 448 stars on GitHub.
- Where can I find One-Shot-Object-Detection?
- timy90022/One-Shot-Object-Detection is on GitHub at https://github.com/timy90022/One-Shot-Object-Detection.