DAFNe: A One-Stage Anchor-Free Deep Model for Oriented Object Detection

by   Steven Lang, et al.

Object detection is a fundamental task in computer vision. While approaches for axis-aligned bounding box detection have made substantial progress in recent years, they perform poorly on oriented objects which are common in several real-world scenarios such as aerial view imagery and security camera footage. In these cases, a large part of a predicted bounding box will, undesirably, cover non-object related areas. Therefore, oriented object detection has emerged with the aim of generalizing object detection to arbitrary orientations. This enables a tighter fit to oriented objects, leading to a better separation of bounding boxes especially in case of dense object distributions. The vast majority of the work in this area has focused on complex two-stage anchor-based approaches. Anchors act as priors on the bounding box shape and require attentive hyper-parameter fine-tuning on a per-dataset basis, increased model size, and come with computational overhead. In this work, we present DAFNe: A Dense one-stage Anchor-Free deep Network for oriented object detection. As a one-stage model, DAFNe performs predictions on a dense grid over the input image, being architecturally simpler and faster, as well as easier to optimize than its two-stage counterparts. Furthermore, as an anchor-free model, DAFNe reduces the prediction complexity by refraining from employing bounding box anchors. Moreover, we introduce an orientation-aware generalization of the center-ness function for arbitrarily oriented bounding boxes to down-weight low-quality predictions and a center-to-corner bounding box prediction strategy that improves object localization performance. DAFNe improves the prediction accuracy over the previous best one-stage anchor-free model results on DOTA 1.0 by 4.65 results by achieving 76.95


page 1

page 6

page 12

page 13

page 14


Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors

Oriented object detection in aerial images is a challenging task as the ...

A General Gaussian Heatmap Labeling for Arbitrary-Oriented Object Detection

Recently, many arbitrary-oriented object detection (AOOD) methods have b...

Segmentation is All You Need

We propose a new paradigm of the detection task that is anchor-box free ...

Oriented Objects as pairs of Middle Lines

The detection of oriented objects is frequently appeared in the field of...

Bounding Maps for Universal Lesion Detection

Universal Lesion Detection (ULD) in computed tomography plays an essenti...

Proposal-free One-stage Referring Expression via Grid-Word Cross-Attention

Referring Expression Comprehension (REC) has become one of the most impo...

Stability analysis of kinetic orientation-based shape descriptors

We study three orientation-based shape descriptors on a set of continuou...

Please sign up or login with your details

Forgot password? Click here to reset