MetaAnchor: Learning to Detect Objects with Customized Anchors
We propose a novel and flexible anchor mechanism named MetaAnchor for object detection frameworks. Unlike many previous detectors model anchors via a predefined manner, in MetaAnchor anchor functions could be dynamically generated from the arbitrary customized prior boxes. Taking advantage of weight prediction, MetaAnchor is able to work with most of the anchor-based object detection systems such as RetinaNet. Compared with the predefined anchor scheme, we empirically find that MetaAnchor is more robust to anchor settings and bounding box distributions; in addition, it also shows the potential on transfer tasks. Our experiment on COCO detection task shows that MetaAnchor consistently outperforms the counterparts in various scenarios.
Code (0)
등록된 구현이 없습니다.
Tasks
Objectobject-detectionObject DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
FreeAnchor: Learning to Match Anchors for Visual Object Detection
Modern CNN-based object detectors assign anchors for ground-truth objects under the restriction of object-anchor Intersection-over-Unit (IoU). In this study, we propose a learning-to-match approach to break IoU restricti…
Objectobject-detectionObject DetectionLayer-wise Customized Weak Segmentation Block and AIoU Loss for Accurate Object Detection
The anchor-based detectors handle the problem of scale variation by building the feature pyramid and directly setting different scales of anchors on each cell in different layers. However, it is difficult for box-wise an…
object-detectionObject DetectionYUDO: YOLO for Uniform Directed Object Detection
This paper presents an efficient way of detecting directed objects by predicting their center coordinates and direction angle. Since the objects are of uniform size, the proposed model works without predicting the object…
Objectobject-detectionObject DetectionReal-Time Object DetectionQAHOI: Query-Based Anchors for Human-Object Interaction Detection
Human-object interaction (HOI) detection as a downstream of object detection tasks requires localizing pairs of humans and objects and extracting the semantic relationships between humans and objects from an image. Recen…
Human-Object Interaction DetectionObjectobject-detectionObject DetectionOriented Objects as pairs of Middle Lines
The detection of oriented objects is frequently appeared in the field of natural scene text detection as well as object detection in aerial images. Traditional detectors for oriented objects are common to rotate anchors …
object-detectionObject DetectionObject Detection In Aerial ImagesOne-stage Anchor-free Oriented Object Detection+3