Enhancing Object Detection for Autonomous Driving by Optimizing Anchor
Generation and Addressing Class Imbalance
- URL: http://arxiv.org/abs/2104.03888v1
- Date: Thu, 8 Apr 2021 16:58:31 GMT
- Title: Enhancing Object Detection for Autonomous Driving by Optimizing Anchor
Generation and Addressing Class Imbalance
- Authors: Manuel Carranza-Garc\'ia, Pedro Lara-Ben\'itez, Jorge
Garc\'ia-Guti\'errez, Jos\'e C. Riquelme
- Abstract summary: This study presents an enhanced 2D object detector based on Faster R-CNN that is better suited for the context of autonomous vehicles.
The proposed modifications over the Faster R-CNN do not increase computational cost and can easily be extended to optimize other anchor-based detection frameworks.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Object detection has been one of the most active topics in computer vision
for the past years. Recent works have mainly focused on pushing the
state-of-the-art in the general-purpose COCO benchmark. However, the use of
such detection frameworks in specific applications such as autonomous driving
is yet an area to be addressed. This study presents an enhanced 2D object
detector based on Faster R-CNN that is better suited for the context of
autonomous vehicles. Two main aspects are improved: the anchor generation
procedure and the performance drop in minority classes. The default uniform
anchor configuration is not suitable in this scenario due to the perspective
projection of the vehicle cameras. Therefore, we propose a perspective-aware
methodology that divides the image into key regions via clustering and uses
evolutionary algorithms to optimize the base anchors for each of them.
Furthermore, we add a module that enhances the precision of the second-stage
header network by including the spatial information of the candidate regions
proposed in the first stage. We also explore different re-weighting strategies
to address the foreground-foreground class imbalance, showing that the use of a
reduced version of focal loss can significantly improve the detection of
difficult and underrepresented objects in two-stage detectors. Finally, we
design an ensemble model to combine the strengths of the different learning
strategies. Our proposal is evaluated with the Waymo Open Dataset, which is the
most extensive and diverse up to date. The results demonstrate an average
accuracy improvement of 6.13% mAP when using the best single model, and of
9.69% mAP with the ensemble. The proposed modifications over the Faster R-CNN
do not increase computational cost and can easily be extended to optimize other
anchor-based detection frameworks.
Related papers
- Scale Optimization Using Evolutionary Reinforcement Learning for Object
Detection on Drone Imagery [17.26524675722299]
This paper proposes an evolutionary reinforcement learning agent, integrated within a coarse-to-fine object detection framework, to optimize the scale for more effective detection of objects in such images.
A set of rewards measuring the localization accuracy, the accuracy of predicted labels, and the scale consistency among nearby patches are designed in the agent to guide the scale optimization.
arXiv Detail & Related papers (2023-12-23T10:49:55Z) - Small Object Detection via Coarse-to-fine Proposal Generation and
Imitation Learning [52.06176253457522]
We propose a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning.
CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A.
arXiv Detail & Related papers (2023-08-18T13:13:09Z) - Adaptive Sparse Convolutional Networks with Global Context Enhancement
for Faster Object Detection on Drone Images [26.51970603200391]
This paper investigates optimizing the detection head based on the sparse convolution.
It suffers from inadequate integration of contextual information of tiny objects.
We propose a novel global context-enhanced adaptive sparse convolutional network.
arXiv Detail & Related papers (2023-03-25T14:42:50Z) - Efficient Person Search: An Anchor-Free Approach [86.45858994806471]
Person search aims to simultaneously localize and identify a query person from realistic, uncropped images.
To achieve this goal, state-of-the-art models typically add a re-id branch upon two-stage detectors like Faster R-CNN.
In this work, we present an anchor-free approach to efficiently tackling this challenging task, by introducing the following dedicated designs.
arXiv Detail & Related papers (2021-09-01T07:01:33Z) - CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented
Object Detection in Remote Sensing Images [0.9462808515258465]
In this paper, we discuss the role of discriminative features in object detection.
We then propose a Critical Feature Capturing Network (CFC-Net) to improve detection accuracy.
We show that our method achieves superior detection performance compared with many state-of-the-art approaches.
arXiv Detail & Related papers (2021-01-18T02:31:09Z) - Anchor-free Small-scale Multispectral Pedestrian Detection [88.7497134369344]
We propose a method for effective and efficient multispectral fusion of the two modalities in an adapted single-stage anchor-free base architecture.
We aim at learning pedestrian representations based on object center and scale rather than direct bounding box predictions.
Results show our method's effectiveness in detecting small-scaled pedestrians.
arXiv Detail & Related papers (2020-08-19T13:13:01Z) - AP-Loss for Accurate One-Stage Object Detection [49.13608882885456]
One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously.
The former suffers much from extreme foreground-background imbalance due to the large number of anchors.
This paper proposes a novel framework to replace the classification task in one-stage detectors with a ranking task.
arXiv Detail & Related papers (2020-08-17T13:22:01Z) - Scope Head for Accurate Localization in Object Detection [135.9979405835606]
We propose a novel detector coined as ScopeNet, which models anchors of each location as a mutually dependent relationship.
With our concise and effective design, the proposed ScopeNet achieves state-of-the-art results on COCO.
arXiv Detail & Related papers (2020-05-11T04:00:09Z) - One-Shot Object Detection without Fine-Tuning [62.39210447209698]
We introduce a two-stage model consisting of a first stage Matching-FCOS network and a second stage Structure-Aware Relation Module.
We also propose novel training strategies that effectively improve detection performance.
Our method exceeds the state-of-the-art one-shot performance consistently on multiple datasets.
arXiv Detail & Related papers (2020-05-08T01:59:23Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.