Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using
Meta-Learning
- URL: http://arxiv.org/abs/2110.03143v1
- Date: Thu, 7 Oct 2021 02:28:18 GMT
- Title: Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using
Meta-Learning
- Authors: Vibashan VS, Domenick Poster, Suya You, Shuowen Hu and Vishal M. Patel
- Abstract summary: Infrared (IR) cameras are robust under adverse illumination and lighting conditions.
We propose an algorithm meta-learning framework to improve existing UDA methods.
We produce a state-of-the-art thermal detector for the KAIST and DSIAC datasets.
- Score: 64.92447072894055
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Object detectors trained on large-scale RGB datasets are being extensively
employed in real-world applications. However, these RGB-trained models suffer a
performance drop under adverse illumination and lighting conditions. Infrared
(IR) cameras are robust under such conditions and can be helpful in real-world
applications. Though thermal cameras are widely used for military applications
and increasingly for commercial applications, there is a lack of robust
algorithms to robustly exploit the thermal imagery due to the limited
availability of labeled thermal data. In this work, we aim to enhance the
object detection performance in the thermal domain by leveraging the labeled
visible domain data in an Unsupervised Domain Adaptation (UDA) setting. We
propose an algorithm agnostic meta-learning framework to improve existing UDA
methods instead of proposing a new UDA strategy. We achieve this by
meta-learning the initial condition of the detector, which facilitates the
adaptation process with fine updates without overfitting or getting stuck at
local optima. However, meta-learning the initial condition for the detection
scenario is computationally heavy due to long and intractable computation
graphs. Therefore, we propose an online meta-learning paradigm which performs
online updates resulting in a short and tractable computation graph. To this
end, we demonstrate the superiority of our method over many baselines in the
UDA setting, producing a state-of-the-art thermal detector for the KAIST and
DSIAC datasets.
Related papers
- Quanv4EO: Empowering Earth Observation by means of Quanvolutional Neural Networks [62.12107686529827]
This article highlights a significant shift towards leveraging quantum computing techniques in processing large volumes of remote sensing data.
The proposed Quanv4EO model introduces a quanvolution method for preprocessing multi-dimensional EO data.
Key findings suggest that the proposed model not only maintains high precision in image classification but also shows improvements of around 5% in EO use cases.
arXiv Detail & Related papers (2024-07-24T09:11:34Z) - PREM: A Simple Yet Effective Approach for Node-Level Graph Anomaly
Detection [65.24854366973794]
Node-level graph anomaly detection (GAD) plays a critical role in identifying anomalous nodes from graph-structured data in domains such as medicine, social networks, and e-commerce.
We introduce a simple method termed PREprocessing and Matching (PREM for short) to improve the efficiency of GAD.
Our approach streamlines GAD, reducing time and memory consumption while maintaining powerful anomaly detection capabilities.
arXiv Detail & Related papers (2023-10-18T02:59:57Z) - Enhancing Visual Domain Adaptation with Source Preparation [5.287588907230967]
Domain Adaptation techniques fail to consider the characteristics of the source domain itself.
We propose Source Preparation (SP), a method to mitigate source domain biases.
We show that SP enhances UDA across a range of visual domains, with improvements up to 40.64% in mIoU over baseline.
arXiv Detail & Related papers (2023-06-16T18:56:44Z) - Spectral Transfer Guided Active Domain Adaptation For Thermal Imagery [1.911678487931003]
We propose an active domain adaptation method to examine the efficiency of combining the visible spectrum and thermal imagery modalities.
We used the large-scale visible spectrum dataset MS-COCO as the source domain and the thermal dataset FLIR ADAS as the target domain.
Our proposed method outperforms the state-of-the-art active domain adaptation methods.
arXiv Detail & Related papers (2023-04-14T10:04:42Z) - Multitask AET with Orthogonal Tangent Regularity for Dark Object
Detection [84.52197307286681]
We propose a novel multitask auto encoding transformation (MAET) model to enhance object detection in a dark environment.
In a self-supervision manner, the MAET learns the intrinsic visual structure by encoding and decoding the realistic illumination-degrading transformation.
We have achieved the state-of-the-art performance using synthetic and real-world datasets.
arXiv Detail & Related papers (2022-05-06T16:27:14Z) - Object Detection in Thermal Spectrum for Advanced Driver-Assistance
Systems (ADAS) [0.5156484100374058]
Object detection in thermal infrared spectrum provides more reliable data source in low-lighting conditions and different weather conditions.
This paper is about exploring and adapting state-of-the-art object and vision framework on thermal vision with seven distinct classes for advanced driver-assistance systems (ADAS)
The trained network variants on public datasets are validated on test data with three different test approaches.
The efficacy of trained networks is tested on locally gathered novel test-data captured with an uncooled LWIR prototype thermal camera.
arXiv Detail & Related papers (2021-09-20T21:38:55Z) - Self-training Guided Adversarial Domain Adaptation For Thermal Imagery [0.12891210250935145]
We propose an unsupervised domain adaptation method which does not require RGB-to-thermal image pairs.
We employ large-scale RGB dataset MS-COCO as source domain and thermal dataset FLIR ADAS as target domain.
To perform self-training, pseudo labels are assigned to the samples on the target thermal domain to learn more generalized representations for the target domain.
arXiv Detail & Related papers (2021-06-14T05:17:21Z) - Cycle and Semantic Consistent Adversarial Domain Adaptation for Reducing
Simulation-to-Real Domain Shift in LiDAR Bird's Eye View [110.83289076967895]
We present a BEV domain adaptation method based on CycleGAN that uses prior semantic classification in order to preserve the information of small objects of interest during the domain adaptation process.
The quality of the generated BEVs has been evaluated using a state-of-the-art 3D object detection framework at KITTI 3D Object Detection Benchmark.
arXiv Detail & Related papers (2021-04-22T12:47:37Z) - Robust pedestrian detection in thermal imagery using synthesized images [39.33977680993236]
We propose a method for improving pedestrian detection in the thermal domain using two stages.
First, a generative data augmentation approach is used, then a domain adaptation method using generated data adapts an RGB pedestrian detector.
Our detector achieves the best single-modality detection results on KAIST with respect to the state-of-the-art.
arXiv Detail & Related papers (2021-02-03T11:08:31Z) - Exploring Thermal Images for Object Detection in Underexposure Regions
for Autonomous Driving [67.69430435482127]
Underexposure regions are vital to construct a complete perception of the surroundings for safe autonomous driving.
The availability of thermal cameras has provided an essential alternate to explore regions where other optical sensors lack in capturing interpretable signals.
This work proposes a domain adaptation framework which employs a style transfer technique for transfer learning from visible spectrum images to thermal images.
arXiv Detail & Related papers (2020-06-01T09:59:09Z)
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.