A Robust Learning Approach to Domain Adaptive Object Detection

Khodabandeh, Mehran; Vahdat, Arash; Ranjbar, Mohammad; Macready, William G.

doi:10.1109/iccv.2019.00057

Cited by 252 publications

(160 citation statements)

References 60 publications

Supporting

Mentioning

160

Contrasting

Order By: Relevance

“…While this research validates their application in cityscapes and other public datasets, it is without a practical-use scenario. Khodabandeh et al [49] inserts noise during pre-processing of the training datasets and DA, which makes the object detection model be resilient to random noise. However, since the idea of object detection with DA is still under development, most related researches are based on a few public datasets with limited practical implementation scenarios, especially in the agriculture domain.…”

Section: Methodsmentioning

confidence: 99%

Augmenting Crop Detection for Precision Agriculture with Deep Visual Transfer Learning—A Case Study of Bale Detection

Zhao

Yamada

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

In recent years, precision agriculture has been researched to increase crop production with less inputs, as a promising means to meet the growing demand of agriculture products. Computer vision-based crop detection with unmanned aerial vehicle (UAV)-acquired images is a critical tool for precision agriculture. However, object detection using deep learning algorithms rely on a significant amount of manually prelabeled training datasets as ground truths. Field object detection, such as bales, is especially difficult because of (1) long-period image acquisitions under different illumination conditions and seasons; (2) limited existing prelabeled data; and (3) few pretrained models and research as references. This work increases the bale detection accuracy based on limited data collection and labeling, by building an innovative algorithms pipeline. First, an object detection model is trained using 243 images captured with good illimitation conditions in fall from the crop lands. In addition, domain adaptation (DA), a kind of transfer learning, is applied for synthesizing the training data under diverse environmental conditions with automatic labels. Finally, the object detection model is optimized with the synthesized datasets. The case study shows the proposed method improves the bale detecting performance, including the recall, mean average precision (mAP), and F measure (F1 score), from averages of 0.59, 0.7, and 0.7 (the object detection) to averages of 0.93, 0.94, and 0.89 (the object detection + DA), respectively. This approach could be easily scaled to many other crop field objects and will significantly contribute to precision agriculture.

show abstract

Section: Methodsmentioning

confidence: 99%

Augmenting Crop Detection for Precision Agriculture with Deep Visual Transfer Learning—A Case Study of Bale Detection

Zhao

Yamada

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Domain Adaptation for Object Detection. Unsupervised domain adaptation for object detection has recently gained interest [17], [46], [20], [47], [18], [48], [49], [50], [22], [21]. Faster R-CNN has been adapted for domain adaptation by aligning the distributions of the last convolutional feature map and the region features [17].…”

Section: Related Workmentioning

confidence: 99%

“…Deep learning based domain adaptive object detection has recently begun to receive attention. Works on this topic can be roughly divided into two categories: feature distribution alignment based methods [17], [18], [19], [20] and selftraining based methods that use pseudo labels [21], [22]. The former approach learns domain-invariant features through adversarial training which uses discriminator networks to predict domain labels for images from the two domains.…”

mentioning

confidence: 99%

AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection

Wang

Liao

Shao

2021

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. Unfortunately, it has received much less attention than supervised object detection. Models that try to address this task tend to suffer from a shortage of annotated training samples. Moreover, existing methods of feature alignments are not sufficient to learn domain-invariant representations. To address these limitations, we propose a novel augmented feature alignment network (AFAN) which integrates intermediate domain image generation and domain-adversarial training into a unified framework. An intermediate domain image generator is proposed to enhance feature alignments by domain-adversarial training with automatically generated soft domain labels. The synthetic intermediate domain images progressively bridge the domain divergence and augment the annotated source domain training data. A feature pyramid alignment is designed and the corresponding feature discriminator is used to align multi-scale convolutional features of different semantic levels. Last but not least, we introduce a region feature alignment and an instance discriminator to learn domaininvariant features for object proposals. Our approach significantly outperforms the state-of-the-art methods on standard benchmarks for both similar and dissimilar domain adaptations. Further extensive experiments verify the effectiveness of each component and demonstrate that the proposed network can learn domain-invariant representations. Index Terms-Object Detection, Unsupervised Domain Adaptation I. INTRODUCTION O BJECT detection is a fundamental problem in computer vision, and has been extensively studied for decades. Over the past several years, deep learning has achieved remarkable success in this area [1], [2], [3]. To advance the state-of-the-art on large-scale benchmarks [4], [5], most deep learning based approaches require tremendous amount of annotated training data.In real-world applications, the manual annotating such large-scale data is time-consuming and laborintensive. Moreover, it is challenging to deploy a trained deep learning model to new environments, even if the task is the same. This is simply because the performance is negatively impacted by changes in conditions such as image sensors, viewpoints, weather and time of day.There is a non-negligible discrepancy between the distribution of data from the target domain and that from the source domain.

show abstract

“…Chen et al [6] add a domain discriminator behind original Faster R-CNN, forcing the original detector to learn domain-invariant features. Khodabandeh et al [18] formulate the domain adaptation as a problem of training with noisy data which enables the detector to improve itself through high confidence predictions and tracking cues. Our method provides another approach for the cross-domain object detection.…”

Section: Related Workmentioning

confidence: 99%