BooDet: Gradient Boosting Object Detection With Additive Learning-Based Prediction Aggregation

In recent years, the community of object detection has witnessed remarkable progress with the development of deep neural networks. But the detection performance still suffers from the dilemma between complex networks and single-vector predictions. In this paper, we propose a novel approach to boost...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing 2022, Vol.31, p.2620-2632
Main Authors: Li, Ya-Li, Wang, Shengjin
Format: Article
Language:English
Subjects:
additive learning
Additives
Annotations
Artificial neural networks
Boosting
Classification
Convolution
Datasets
deep neural networks
Detectors
Feature extraction
gradient boosting
Location awareness
Machine learning
Neural Networks, Computer
Object detection
Object recognition
Optimization
Regression
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In recent years, the community of object detection has witnessed remarkable progress with the development of deep neural networks. But the detection performance still suffers from the dilemma between complex networks and single-vector predictions. In this paper, we propose a novel approach to boost the object detection performance based on aggregating predictions. First, we propose a unified module with adjustable hyper-structure to generate multiple predictions from a single detection network. Second, we formulate the additive learning for aggregating predictions, which reduces the classification and regression losses by progressively adding the prediction values. Based on the gradient Boosting strategy, the optimization of the additional predictions is further modeled as weighted regression problems to fit the Newton-descent directions. By aggregating multiple predictions from a single network, we propose the BooDet approach which can Boo tstrap the classification and bounding box regression for high-performance object Det ection. In particular, we plug the BooDet into Cascade R-CNN for object detection. Extensive experiments show that the proposed approach is quite effective to improve object detection. We obtain a 1.3%~2.0% improvement over the strong baseline Cascade R-CNN on COCO val dataset. We achieve 56.5% AP on the COCO test-dev dataset with only bounding box annotations.
ISSN:1057-7149
1941-0042
DOI:10.1109/TIP.2022.3157453