Gaussian Guided IoU: A Better Metric for Balanced Learning on Object Detection

03/25/2021
by   Shengkai Wu, et al.
0

For most of the anchor-based detectors, Intersection over Union(IoU) is widely utilized to assign targets for the anchors during training. However, IoU pays insufficient attention to the closeness of the anchor's center to the truth box's center. This results in two problems: (1) only one anchor is assigned to most of the slender objects which leads to insufficient supervision information for the slender objects during training and the performance on the slender objects is hurt; (2) IoU can not accurately represent the alignment degree between the receptive field of the feature at the anchor's center and the object. Thus during training, some features whose receptive field aligns better with objects are missing while some features whose receptive field aligns worse with objects are adopted. This hurts the localization accuracy of models. To solve these problems, we firstly design Gaussian Guided IoU(GGIoU) which focuses more attention on the closeness of the anchor's center to the truth box's center. Then we propose GGIoU-balanced learning method including GGIoU-guided assignment strategy and GGIoU-balanced localization loss. The method can assign multiple anchors for each slender object and bias the training process to the features well-aligned with objects. Extensive experiments on the popular benchmarks such as PASCAL VOC and MS COCO demonstrate GGIoU-balanced learning can solve the above problems and substantially improve the performance of the object detection model, especially in the localization accuracy.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/18/2022

RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection

Detecting tiny objects is one of the main obstacles hindering the develo...
research
09/29/2020

Localize to Classify and Classify to Localize: Mutual Guidance in Object Detection

Most deep learning object detectors are based on the anchor mechanism an...
research
11/02/2022

TSAA: A Two-Stage Anchor Assignment Method towards Anchor Drift in Crowded Object Detection

Among current anchor-based detectors, a positive anchor box will be intu...
research
09/05/2019

FreeAnchor: Learning to Match Anchors for Visual Object Detection

Modern CNN-based object detectors assign anchors for ground-truth object...
research
12/02/2018

Anchor Box Optimization for Object Detection

In this paper, we propose a general approach to optimize anchor boxes fo...
research
08/23/2021

Towards Balanced Learning for Instance Recognition

Instance recognition is rapidly advanced along with the developments of ...
research
06/28/2020

Localization Uncertainty Estimation for Anchor-Free Object Detection

Since many safety-critical systems such as surgical robots and autonomou...

Please sign up or login with your details

Forgot password? Click here to reset