In this work, we aim to solve the problem of few-shot object detection. This problem makes the few-shot object detection intrinsically different from the few-shot classification. This could be due to the improper low scores of good bounding boxes in a region proposal network (RPN), which makes an novel object hard to be detected. It happens that the potential bounding boxes would perfectly miss the unseen objects or have many false detection on background. Object detection from few shots usually confronts one crucial problem, that is how to localize an unseen object in a cluttered background, namely a generalization problem of object localization from a few training examples of novel categories. This is because transferring the experiences from few-shot classification to few-shot object detection is a non-trivial task. These methods, however, all focus on image classification, and the few-shot object detection is rarely exploited. In recent years, it has achieved great progresses. Given different objects as supports, our approach can detect all objects with same categories in the given query image.įew-Shot learning is challenging due to the large object variance of illumination, shape, texture \etc, in the real world. 1 Introduction Figure 1: Explanation of our approach. We demonstrate the effectiveness of our method quantitatively and qualitatively on different datasets. Our method is general, and has a wide range of applications. This is also the major advantage of few shot object detection. Once our network is trained, we can apply object detection for unseen classes without further training or fine tuning. To the best of our knowledge, this is also the first dataset specifically designed for few shot object detection. To train our network, we have prepared a new dataset which contains 1000 categories of varies objects with high quality annotations. Central to our method is the Attention-RPN and the multi-relation module which fully exploit the similarity between the few shot training examples and the test set to detect novel objects while suppressing the false detection in background. In this paper, we propose few-shot object detection which aims to detect objects of unseen class with a few training examples. Conventional methods for object detection usually requires substantial amount of training data and to prepare such high quality training data is labor intensive.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |