Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learning

VS, Vibashan; Poster, Domenick; You, Suya; Hu, Shuowen; Patel, Vishal M.

doi:10.1109/wacv51458.2022.00375

Cited by 22 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this experiment, we detect and crop the ATR vehicles from the DSIAC dataset by using the information from the Meta-UDA. 23 The different distances of target vehicles are projected into the canonical distance (2 kilometers) using bi-cubic interpolation. The final target chip size is 68x68x3.…”

Section: Datasetmentioning

confidence: 99%

Deep transductive transfer learning for automatic target recognition

Sami

Nasrabadi

Rao

2023

Automatic Target Recognition XXXIII

View full text Add to dashboard Cite

One of the major obstacles in designing an automatic target recognition (ATR) algorithm, is that there are often labeled images in one domain (i.e., infrared source domain) but no annotated images in the other target domains (i.e., visible, SAR, LIDAR). Therefore, automatically annotating these images is essential to build a robust classifier in the target domain based on the labeled images of the source domain. Transductive transfer learning is an effective way to adapt a network to a new target domain by utilizing a pretrained ATR network in the source domain. We propose an unpaired transductive transfer learning framework where a CycleGAN model and a well-trained ATR classifier in the source domain are used to construct an ATR classifier in the target domain without having any labeled data in the target domain. We employ a CycleGAN model to transfer the mid-wave infrared (MWIR) images to visible (VIS) domain images (or visible to MWIR domain). To train the transductive CycleGAN, we optimize a cost function consisting of the adversarial, identity, cycle-consistency, and categorical cross-entropy loss for both the source and target classifiers. In this paper, we perform a detailed experimental analysis on the challenging DSIAC ATR dataset. The dataset consists of ten classes of vehicles at different poses and distances ranging from 1-5 kilometers on both the MWIR and VIS domains. In our experiment, we assume that the images in the VIS domain are the unlabeled target dataset. We first detect and crop the vehicles from the raw images and then project them into a common distance of 2 kilometers. Our proposed transductive CycleGAN achieves 71.56% accuracy in classifying the visible domain vehicles in the DSIAC ATR dataset.

show abstract

Section: Datasetmentioning

confidence: 99%

Deep transductive transfer learning for automatic target recognition

Sami

Nasrabadi

Rao

2023

Automatic Target Recognition XXXIII

View full text Add to dashboard Cite

show abstract

“…In support of the thermal ATR task, Abraham et al [ 33 ] improve the performance of YOLOv5 models on the DSIAC dataset via a novel homotopy-based hyperparameter optimization algorithm. Leveraging the visible imagery of the DSIAC dataset, VS et al [ 34 ] propose a metalearning strategy for unsupervised domain adaptation in thermal ATR.…”

Section: Related Workmentioning

confidence: 99%

Long-Range Thermal Target Detection in Data-Limited Settings Using Restricted Receptive Fields

Poster,

Hu,

Nasrabadi

2023

Sensors

Self Cite

View full text Add to dashboard Cite

Long-range target detection in thermal infrared imagery is a challenging research problem due to the low resolution and limited detail captured by thermal sensors. The limited size and variability in thermal image datasets for small target detection is also a major constraint for the development of accurate and robust detection algorithms. To address both the sensor and data constraints, we propose a novel convolutional neural network (CNN) feature extraction architecture designed for small object detection in data-limited settings. More specifically, we focus on long-range ground-based thermal vehicle detection, but also show the effectiveness of the proposed algorithm on drone and satellite aerial imagery. The design of the proposed architecture is inspired by an analysis of popular object detectors as well as custom-designed networks. We find that restricted receptive fields (rather than more globalized features, as is the trend), along with less downsampling of feature maps and attenuated processing of fine-grained features, lead to greatly improved detection rates while mitigating the model’s capacity to overfit on small or poorly varied datasets. Our approach achieves state-of-the-art results on the Defense Systems Information Analysis Center (DSIAC) automated target recognition (ATR) and the Tiny Object Detection in Aerial Images (AI-TOD) datasets.

show abstract

“…They transfer the visible domain into the thermal domain by image adaptation such as Guo et al [22] and Kieu et al [21] or feature adaptation such as Herrmann [14], Kieu et al [19], Kieu et al [20] and Kim et al [45]. The final one is unsupervised domain adaptation, such as Meta-UDA [46]. Disentanglement Learning.…”

Section: Related Workmentioning

confidence: 99%

Thermal pedestrian detection based on different resolution visual image

Li¹,

Cui²,

Ye³

et al. 2023

SIViP

View full text Add to dashboard Cite

Thermal pedestrian detection is a core problem in computer vision. Usually, the corresponding visual image knowledge are used to improve the performance in thermal domain. However, existing methods always assume the same resolution between visible and thermal images. But in reality, there is a problem with this setting. Since thermal imaging acquisition equipment is expensive, the resolution of thermal images is always lower than visible images. To address this issue, we propose a new method, named as Disentanglement Then Restoration (DTR).

show abstract

Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learning

Cited by 22 publications

References 25 publications

Deep transductive transfer learning for automatic target recognition

Deep transductive transfer learning for automatic target recognition

Long-Range Thermal Target Detection in Data-Limited Settings Using Restricted Receptive Fields

Thermal pedestrian detection based on different resolution visual image

Contact Info

Product

Resources

About