Cross-Domain Adaptive Teacher for Object Detection

Li, Yu-Jhe; Dai, Xiaoliang; Ma, Chih-Yao; Liu, Yen‐Cheng; Chen, Kan; Wu, Bichen; He, Zhongshi; Vajda, Péter

doi:10.1109/cvpr52688.2022.00743

Cited by 132 publications

(86 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Domain adaptation methods seek to align the source domain distribution to a particular target domain. To bridge the global and instance-level domain gaps, [3,5,41,43] learn feature alignment via [15] adversarial training; [58] and [46] utilize category-level centroids and attention maps, respectively, to better align instances in the two domains; [8,30] generate pseudo-labels in the target domain and use them for targetaware training. Domain adaptation, however, assumes that images from the target domain are available during training.…”

Section: Related Workmentioning

confidence: 99%

“…As for most machine learning models, the performance of object detectors degrades when the test data distribution deviates from the training data one. Domain adaptation techniques [3,5,8,30,41,43] try to alleviate this problem by learning domain invariant features between a source and a known target domain. In practice, however, it is not always possible to obtain target data, even unlabeled, precluding the use of such techniques.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

CLIP the Gap: A Single Domain Generalization Approach for Object Detection

Vidit¹,

Engilberge²,

Salzmann³

2023

Preprint

View full text Add to dashboard Cite

Single Domain Generalization (SDG) tackles the problem of training a model on a single source domain so that it generalizes to any unseen target domain. While this has been well studied for image classification, the literature on SDG object detection remains almost non-existent. To address the challenges of simultaneously learning robust object localization and representation, we propose to leverage a pre-trained vision-language model to introduce semantic domain concepts via textual prompts. We achieve this via a semantic augmentation strategy acting on the features extracted by the detector backbone, as well as a text-based classification loss. Our experiments evidence the benefits of our approach, outperforming by 10% the only existing SDG object detection method, Single-DGOD [49], on their own diverse weather-driving benchmark.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

CLIP the Gap: A Single Domain Generalization Approach for Object Detection

Vidit¹,

Engilberge²,

Salzmann³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Domain adaptation (DA) is one type of transfer learning, and it learns a model from a well-annotated source domain and generalizes well to an unlabeled target domain (Li et al, 2022). The prevalent idea in addressing the DA problem of object detection is based on an adversarial learning manner to align feature distributions across domains, which helps the detector to produce domain-invariant features.…”

Section: Domain Adaptation In Object Detectionmentioning

confidence: 99%

Soft-masks guided faster region-based convolutional neural network for domain adaptation in wind turbine detection

Luo

Yuan

et al. 2023

Front. Energy Res.

View full text Add to dashboard Cite

Wind turbine generator system plays a fundamental role in electricity generation in industry 4.0, and wind turbines are usually distributed separately and in poor locations. Unmanned Aerial Vehicles (UAV) which could overcome the above challenges are deployed to collect photographs of wind turbines, could be used for predictive maintenance of wind turbines and energy management. However, identifying meaningful information from huge amounts of photographs taken by drones is a challenging task due to various scales, different viewpoints, and tedious manual annotation. Besides, deep neural networks (DNN) are dominant in object detection, and training DNN requires large numbers of accurately labeled training data, and manual data annotation is tedious, inefficient, and error-prone. Considering these issues, we generate a synthetic UAV-taken dataset of wind turbines, which provides RGB images, target bounding boxes, and precise pixel annotations as well. But directly transferring the model trained on the synthetic dataset to the real dataset may lead to poor performance due to domain shifts (or domain gaps). The predominant approaches to alleviate the domain discrepancy are adversarial feature learning strategies, which focus on feature alignment for style (e.g., color, texture, illumination, etc.) gaps without considering the content (e.g., densities, backgrounds, and layout scenes) gaps. In this study, we scrutinize the real UAV-taken imagery of wind turbines and develop a synthetic generation method trying to simulate the real ones from the aspects of style and content. Besides, we propose a novel soft-masks guided faster region-based convolutional neural network (SMG Faster R-CNN) for domain adaptation in wind turbine detection, where the soft masks help to extract highly object-related features and suppress domain-specific features. We evaluate the accuracy of SMG Faster R-CNN on the wind turbine dataset and demonstrate the effectiveness of our approach compared with some prevalent object detection models and some adversarial DA models.

show abstract

“…Compared with AT [ 51 ] and MT [ 50 ], our model achieved the best performance in several categories. Despite this, in some categories (such as bicycle, dog, and person), our method is not achieving the optimal performance, but we can observe that their differences of average precision is actually not large.…”

Section: Experiments and Analysismentioning

confidence: 99%

Cross-Domain Object Detection by Dual Adaptive Branch

Liu

Zhang

Liu

2023

Sensors

View full text Add to dashboard Cite

The object detection task usually assumes that the training and test samples obey the same distribution, and this assumption is not valid in reality, therefore the study of cross-domain object detection is proposed. Compared with image classification, the cross-domain object detection task presents the greater challenge, which requires both accurate classification and localization of samples in the target domain. The teacher–student framework (the student model is supervised by pseudo-labels from the teacher model) has produced a large accuracy improvement in cross-domain object detection. Feature-level adversarial training is used in the student model, which allows features in the source and target domains to share a similar distribution. However, the direction and gradient of the weights can be divided into domain-specific and domain-invariant features, and the purpose of domain adaptive is to focus on the domain-invariant features while eliminating interference from the domain-specific features. Inspired by this, we propose a teacher–student framework named dual adaptive branch (DAB), which uses domain adversarial learning to address the domain distribution. Specifically, we ensure that the student model aligns domain-invariant features and suppresses domain-specific features in this process. We further validate our method based on multiple domains. The experimental results demonstrate that our proposed method significantly improves the performance of cross-domain object detection and achieves the competitive experimental results on common benchmarks.

show abstract

Cross-Domain Adaptive Teacher for Object Detection

Cited by 132 publications

References 32 publications

CLIP the Gap: A Single Domain Generalization Approach for Object Detection

CLIP the Gap: A Single Domain Generalization Approach for Object Detection

Soft-masks guided faster region-based convolutional neural network for domain adaptation in wind turbine detection

Cross-Domain Object Detection by Dual Adaptive Branch

Contact Info

Product

Resources

About