https://scholars.lib.ntu.edu.tw/handle/123456789/607485
標題: | Class-agnostic few-shot object counting | 作者: | Yang S.-D Su H.-T WEN-CHIN CHEN WINSTON HSU |
關鍵字: | Counting networks;Data collection;Learn+;Mechanical arm;Object class;Object counting;Parameters tuning;Pre-defined class;Query images;Reference image;Computer vision | 公開日期: | 2021 | 起(迄)頁: | 869-877 | 來源出版物: | Proceedings - 2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021 | 摘要: | Object counting which aims to calculate the number of total instances of the given class is a classic but crucial task that can be applied to many applications. Most of the prior works only focus on counting certain classes of objects such as people, cars, animals, etc. However, in recent years, there are lots of applications that need to get the count of the unseen class of objects such as a mechanical arm commanded to grab the novel object. In this paper, we present an effective object counting network, Class-agnostic Few-shot Object Counting Network (CFOCNet), that supports counting arbitrary classes of object unseen during training stage. Instead of counting a pre-defined class, our model is able to count instances based on input reference images and reduces the huge cost of data collection, training and parameter tuning for each new object class. Our model utilizes not only the similarity between query image and reference images but self attending the query image to learn the self-repeatedness. Using a two-stream Resnet that matches features in different scales, our network can automatically learn to aggregate different scales of the matching scores. We evaluate our method on the subset of the COCO dataset that contains 80 classes of objects and many diverse scenes. In the experiments, our network outperforms other methods including detection and some previous works by a large margin. To the best of our knowledge, we are the first that mainly focuses on few-shot object counting in the class-agnostic manner. ? 2021 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85116082989&doi=10.1109%2fWACV48630.2021.00091&partnerID=40&md5=0c41556beec478ddfd82066ef0e61323 https://scholars.lib.ntu.edu.tw/handle/123456789/607485 |
DOI: | 10.1109/WACV48630.2021.00091 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。