SINGLE-SHOT SEMANTIC MATCHER FOR UNSEEN OBJECT DETECTION
نویسندگان
چکیده
منابع مشابه
Single-Shot Object Detection with Enriched Semantics
We propose a novel single shot object detection network named Detection with Enriched Semantics (DES). Our motivation is to enrich the semantics of object detection features within a typical deep detector, by a semantic segmentation branch and a global activation module. The segmentation branch is supervised by weak segmentation ground-truth, i.e., no extra annotation is required. In conjunctio...
متن کاملSingle-Shot Refinement Neural Network for Object Detection
For object detection, the two-stage approach (e.g., Faster R-CNN) has been achieving the highest accuracy, whereas the one-stage approach (e.g., SSD) has the advantage of high efficiency. To inherit the merits of both while overcoming their disadvantages, in this paper, we propose a novel single-shot based detector, called RefineDet, that achieves better accuracy than two-stage methods and main...
متن کاملSingle-Shot Bidirectional Pyramid Networks for High-Quality Object Detection
Recent years have witnessed many exciting achievements for object detection using deep learning techniques. Despite achieving significant progresses, most existing detectors are designed to detect objects with relatively lowquality prediction of locations, i.e., often trained with the threshold of Intersection over Union (IoU) set to 0.5 by default, which can yield low-quality or even noisy det...
متن کاملEfficient Semantic Video Annotation by Object and Shot Re-Detection
Manual video annotation on shot and on object level is a very time consuming and therefore cost intensive task. Automatic object and shot re-detection is one step forward in order to provide a cost efficient solution for temporally detailed video annotation. In this demonstration a tool will be shown which integrates novel video visualisation, navigation and interactive object re-detection tech...
متن کاملFew-shot Object Detection
In this paper, we study object detection using a large pool of unlabeled images and only a few labeled images per category, named “few-shot object detection”. The key challenge consists in generating trustworthy training samples as many as possible from the pool. Using few training examples as seeds, our method iterates between model training and high-confidence sample selection. In training, e...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
سال: 2018
ISSN: 2194-9034
DOI: 10.5194/isprs-archives-xlii-2-379-2018