TricubeNet: 2D Kernel-Based Object Representation for Weakly-Occluded Oriented Object Detection

23 Apr 2021  ·  Beomyoung Kim, Janghyeon Lee, Sihaeng Lee, Doyeon Kim, Junmo Kim ·

We present a novel approach for oriented object detection, named TricubeNet, which localizes oriented objects using visual cues ($i.e.,$ heatmap) instead of oriented box offsets regression. We represent each object as a 2D Tricube kernel and extract bounding boxes using simple image-processing algorithms. Our approach is able to (1) obtain well-arranged boxes from visual cues, (2) solve the angle discontinuity problem, and (3) can save computational complexity due to our anchor-free modeling. To further boost the performance, we propose some effective techniques for size-invariant loss, reducing false detections, extracting rotation-invariant features, and heatmap refinement. To demonstrate the effectiveness of our TricubeNet, we experiment on various tasks for weakly-occluded oriented object detection: detection in an aerial image, densely packed object image, and text image. The extensive experimental results show that our TricubeNet is quite effective for oriented object detection. Code is available at https://github.com/qjadud1994/TricubeNet.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Object Detection In Aerial Images DOTA TricubeNet mAP 75.26% # 41
Oriented Object Detection DOTA 1.0 TricubeNet mAP 75.26 # 10
One-stage Anchor-free Oriented Object Detection SKU110K-R TricubeNet AP@50 94.7 # 1
AP 57.7 # 1
AP@75 65.2 # 2

Methods