Target-Style-Aware Unsupervised Domain Adaptation for Object Detection

Yun, Woo-han; Han, ByungOk; Lee, Jaeyeon; Kim, Jae Hong; Kim, Junmo

doi:10.1109/lra.2021.3062333

Cited by 3 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These strategies can be applied at different feature extraction stages of the object detection model. Data manipulation-based methods directly augment (Prakash et al, 2019;Wang et al, 2021a) or perform style transformations (Yun et al, 2021;Yu et al, 2022) on input data to narrow the distribution gap between the source and target domains. Learning strategy-based methods achieve object detection of target domain by introducing some learning strategies like self-training (Zhao et al, 2020a;Li et al, 2021) and teacher-student networks (He et al, 2022;Li et al, 2022b).…”

Section: Domain Adaptive Object Detectionmentioning

confidence: 99%

Frequency Domain Disentanglement for Arbitrary Neural Style Transfer

Luo

Wang

et al. 2023

AAAI

View full text Add to dashboard Cite

Arbitrary neural style transfer has been a popular research topic due to its rich application scenarios. Effective disentanglement of content and style is the critical factor for synthesizing an image with arbitrary style. The existing methods focus on disentangling feature representations of content and style in the spatial domain where the content and style components are innately entangled and difficult to be disentangled clearly. Therefore, these methods always suffer from low-quality results because of the sub-optimal disentanglement. To address such a challenge, this paper proposes the frequency mixer (FreMixer) module that disentangles and re-entangles the frequency spectrum of content and style components in the frequency domain. Since content and style components have different frequency-domain characteristics (frequency bands and frequency patterns), the FreMixer could well disentangle these two components. Based on the FreMixer module, we design a novel Frequency Domain Disentanglement (FDD) framework for arbitrary neural style transfer. Qualitative and quantitative experiments verify that the proposed method can render better stylized results compared to the state-of-the-art methods.

show abstract

Section: Domain Adaptive Object Detectionmentioning

confidence: 99%

Frequency Domain Disentanglement for Arbitrary Neural Style Transfer

Luo

Wang

et al. 2023

AAAI

View full text Add to dashboard Cite

show abstract

“…By bridging the domain gap on the premise of ensuring the performance of source classification task, DA can adapt the model learned from the source domain to the target in the presence of data bias, which solves the dilemma of label scarcity in many real-world applications [59,51,14,49,3,61]. Extensive DA approaches have been proposed in recent years, achieving great performances in many areas such as image classification [14,31,60], semantic segmentation [53,56,19], and object detection [43,47,58].…”

Section: Introductionmentioning

confidence: 99%

Pareto Domain Adaptation

Liang

Gong

et al. 2021

Preprint

View full text Add to dashboard Cite

Domain adaptation (DA) attempts to transfer the knowledge from a labeled source domain to an unlabeled target domain that follows different distribution from the source. To achieve this, DA methods include a source classification objective L S to extract the source knowledge and a domain alignment objective L D to diminish the domain shift, ensuring knowledge transfer. Typically, former DA methods adopt some weight hyper-parameters to linearly combine the training objectives to form an overall objective L. However, the gradient directions of these objectives may conflict with each other due to domain shift. Under such circumstances, the linear optimization scheme might decrease the overall objective value at the expense of damaging one of the training objectives, leading to restricted solutions. In this paper, we rethink the optimization scheme for DA from a gradient-based perspective. We propose a Pareto Domain Adaptation (ParetoDA) approach to control the overall optimization direction, aiming to cooperatively optimize all training objectives. Specifically, to reach a desirable solution on the target domain, we design a surrogate loss mimicking target classification. To improve target-prediction accuracy to support the mimicking, we propose a target-prediction refining mechanism which exploits domain labels via Bayes' theorem. On the other hand, since prior knowledge of weighting schemes for objectives is often unavailable to guide optimization to approach the optimal solution on the target domain, we propose a dynamic preference mechanism to dynamically guide our cooperative optimization by the gradient of the surrogate loss on a held-out unlabeled target dataset. Our theoretical analyses show that the held-out data can guide but will not be over-fitted by the optimization. Extensive experiments on image classification and semantic segmentation benchmarks demonstrate the effectiveness of ParetoDA. Our code is available at https://github.com/BIT-DA/ParetoDA.

show abstract

Deep Domain Adaptive Object Detection: a Survey

Luo

et al. 2020

2020 IEEE Symposium Series on Computational Intelligence (SSCI)

View full text Add to dashboard Cite

Deep learning (DL) based object detection has achieved great progress. These methods typically assume that large amount of labeled training data is available, and training and test data are drawn from an identical distribution. However, the two assumptions are not always hold in practice. Deep domain adaptive object detection (DDAOD) has emerged as a new learning paradigm to address the above mentioned challenges. This paper aims to review the state-of-the-art progress on deep domain adaptive object detection approaches. Firstly, we introduce briefly the basic concepts of deep domain adaptation. Secondly, the deep domain adaptive detectors are classified into four categories and detailed descriptions of representative methods in each category are provided. Finally, insights for future research trend are presented.

show abstract

Target-Style-Aware Unsupervised Domain Adaptation for Object Detection

Cited by 3 publications

References 27 publications

Frequency Domain Disentanglement for Arbitrary Neural Style Transfer

Frequency Domain Disentanglement for Arbitrary Neural Style Transfer

Pareto Domain Adaptation

Deep Domain Adaptive Object Detection: a Survey

Contact Info

Product

Resources

About