Detect objects in new domains having different camera viewpoints and field-of-views with Vidit

Detect objects in new domains having different camera viewpoints and field-of-views with Vidit

Learning Transformations To Reduce the Geometric Shift in Object Detection

arXiv paper abstract https://arxiv.org/abs/2301.05496

arXiv PDF paper https://arxiv.org/pdf/2301.05496.pdf

The performance of modern object detectors drops when the test distribution differs from the training one.

Most of the methods that address this focus on object appearance changes caused by, e.g., different illumination conditions, or gaps between synthetic and real images.

Here, by contrast, ... tackle geometric shifts emerging from variations in the image capture process, or due to the constraints of the environment causing differences in the apparent geometry of the content itself.

... introduce a self-training approach that learns a set of geometric transformations to minimize these shifts without leveraging any labeled data in the new domain, nor any information about the cameras.

... evaluate ... method on two different shifts, i.e., a camera's field of view (FoV) change and a viewpoint change.

... results evidence that learning geometric transformations helps detectors to perform better in the target domains.

Please like and share this post if you enjoyed it using the buttons at the bottom! Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact Web site with my other posts by category https://morrislee1234.wixsite.com/website LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b #ComputerVision #ObjectDetection #AINewsClips #AI #ML #ArtificialIntelligence #MachineLearning