OS2D: One-Stage One-Shot Object Detection by Matching Anchor Features
This work addresses the problem of detecting unseen object classes from minimal examples, which is crucial for applications like robotics and retail, but it is incremental as it builds on existing one-shot detection methods with novel components.
The paper tackles one-shot object detection, where objects are detected from a single demonstration and training and testing classes do not overlap, by building a one-stage system that jointly performs localization and recognition using dense correlation matching and geometric transformation, achieving significant performance improvements over baselines across multiple domains such as retail products and 3D objects.
In this paper, we consider the task of one-shot object detection, which consists in detecting objects defined by a single demonstration. Differently from the standard object detection, the classes of objects used for training and testing do not overlap. We build the one-stage system that performs localization and recognition jointly. We use dense correlation matching of learned local features to find correspondences, a feed-forward geometric transformation model to align features and bilinear resampling of the correlation tensor to compute the detection score of the aligned features. All the components are differentiable, which allows end-to-end training. Experimental evaluation on several challenging domains (retail products, 3D objects, buildings and logos) shows that our method can detect unseen classes (e.g., toothpaste when trained on groceries) and outperforms several baselines by a significant margin. Our code is available online: https://github.com/aosokin/os2d .