Towards Accurate Localization by Instance Search
Visual object localization is the key step in a series of object detection tasks. In the literature, high localization accuracy is achieved with the mainstream strongly supervised frameworks. However, such methods require object-level annotations and are unable to detect objects of unknown categories. Weakly supervised methods face similar difficulties. In this paper, a self-paced learning framework is proposed to achieve accurate object localization on the rank list returned by instance search. The proposed framework mines the target instance gradually from the queries and their corresponding top-ranked search results. Since a common instance is shared between the query and the images in the rank list, the target visual instance can be accurately localized even without knowing what the object category is. In addition to performing localization on instance search, the issue of few-shot object detection is also addressed under the same framework. Superior performance over state-of-the-art methods is observed on both tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Few-Shot Object DetectionInstance SearchObjectobject-detectionObject DetectionObject LocalizationSimilar Papers 제목 키워드 기반
Efficient Large-Scale Localization by Global Instance Recognition
Hierarchical frameworks consisting of both coarse and fine localization are often used as the standard pipeline for large-scale visual localization. Despite their promising performance in simple environments, they st…
Visual LocalizationDive Deeper Into Box for Object Detection
Anchor free methods have defined the new frontier in state-of-the-art object detection researches where accurate bounding box estimation is the key to the success of these methods. However, even the bounding box has the …
Objectobject-detectionObject DetectionRobust Object Detection With Inaccurate Bounding Boxes
Learning accurate object detectors often requires large-scale training data with precise object bounding boxes. However, labeling such data is expensive and time-consuming. As the crowd-sourcing labeling process and the …
Multiple Instance LearningObjectobject-detectionObject Detection+1Learning Independent Instance Maps for Crowd Localization
Accurately locating each head's position in the crowd scenes is a crucial task in the field of crowd analysis. However, traditional density-based methods only predict coarse prediction, and segmentation/detection-based m…
BinarizationSegmentationUnambiguous Text Localization and Retrieval for Cluttered Scenes
Text instance as one category of self-described objects provides valuable information for understanding and describing cluttered scenes. In this paper, we explore the task of unambiguous text localization and retrieval, …
RetrievalText Retrieval