Scale variance minimization for unsupervised domain adaptation in image segmentation

Guan, Dayan; Huang, Jiaxing; Lu, Shijian; Xiao, Aoran

doi:10.1016/j.patcog.2020.107764

Cited by 71 publications

(34 citation statements)

References 33 publications

(93 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the success of Generative Adversarial Network (GAN) [44], researchers have proposed to construct adversarial loss [1] for domain adaptation. Various adversarial based domain adaptation methods [1,45,46,47,3] have been proposed for a wide range of image-based tasks, such as image recognition [1,2,48,3], object detection [4,5,49], semantic segmentation [50,51,52,53] and person reidentification [54,7].…”

Section: Unsupervised Domain Adaptationmentioning

confidence: 99%

Aligning Correlation Information for Domain Adaptation in Action Recognition

Yang

Cao

et al. 2021

Preprint

View full text Add to dashboard Cite

Domain adaptation (DA) approaches address domain shift and enable networks to be applied to different scenarios. Although various image DA approaches have been proposed in recent years, there is limited research towards video DA. This is partly due to the complexity in adapting the different modalities of features in videos, which includes the correlation features extracted as long-term dependencies of pixels across spatiotemporal dimensions. The correlation features are highly associated with action classes and proven their effectiveness in accurate video feature extraction through the supervised action recognition task. Yet correlation features of the same action would differ across domains due to domain shift. Therefore we propose a novel Adversarial Correlation Adaptation Network (ACAN) to align action videos by aligning pixel correlations. ACAN aims to minimize the distribution of correlation information, termed as Pixel Correlation Discrepancy (PCD). Additionally, video DA research is also limited by the lack of cross-domain video datasets with larger domain shifts.We, therefore, introduce a novel HMDB-ARID dataset with a larger domain shift caused by a larger statistical difference between domains. This dataset is built in an effort to leverage current datasets for dark video classification.

show abstract

Section: Unsupervised Domain Adaptationmentioning

confidence: 99%

Aligning Correlation Information for Domain Adaptation in Action Recognition

Yang

Cao

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The second category is image translation based which adapt image appearance to mitigate domain gaps [25,75,12,45,98,27,94,31,29]. The third category is self-training based which predict pseudo labels or minimize entropy to guide iterative learning from target samples [104,73,101,103,19,30]. Domain adaptation involves two typical training losses, namely, supervised loss over labeled source data and unsupervised loss over unlabeled target data.…”

Section: Related Workmentioning

confidence: 99%

RDA: Robust Domain Adaptation via Fourier Adversarial Attacking

Huang

Guan

Xiao

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Unsupervised domain adaptation (UDA) involves a supervised loss in a labeled source domain and an unsupervised loss in an unlabeled target domain, which often faces more severe overfitting (than classical supervised learning) as the supervised source loss has clear domain gap and the unsupervised target loss is often noisy due to the lack of annotations. This paper presents RDA, a robust domain adaptation technique that introduces adversarial attacking to mitigate overfitting in UDA. We achieve robust domain adaptation by a novel Fourier adversarial attacking (FAA) method that allows large magnitude of perturbation noises but has minimal modification of image semantics, the former is critical to the effectiveness of its generated adversarial samples due to the existence of 'domain gaps'. Specifically, FAA decomposes images into multiple frequency components (FCs) and generates adversarial samples by just perturbating certain FCs that capture little semantic information. With FAA-generated samples, the training can continue the 'random walk' and drift into an area with a flat loss landscape, leading to more robust domain adaptation. Extensive experiments over multiple domain adaptation tasks show that RDA can work with different computer vision tasks with superior performance.

show abstract

“…Domain adaptive image segmentation has been widely investigated to address the image annotation challenge and domain shift issues [7,65]. Most existing methods take two typical approaches, namely, adversarial learning based [24,59,62,60,40,26,50,21] 35,36,65,32,67,44]. The adversarial learning based methods perform domain alignment by adopting a discriminator that strives to differentiate the segmentation in the space of inputs [24,66,35,12,32], features [61,24,11,66,40] or outputs [59,62,41,60,26,42,63,50,21].…”

Section: Domain Adaptive Image Segmentationmentioning

confidence: 99%

“…Most existing methods take two typical approaches, namely, adversarial learning based [24,59,62,60,40,26,50,21] 35,36,65,32,67,44]. The adversarial learning based methods perform domain alignment by adopting a discriminator that strives to differentiate the segmentation in the space of inputs [24,66,35,12,32], features [61,24,11,66,40] or outputs [59,62,41,60,26,42,63,50,21]. The self-training based methods exploit self-training to predict pseudo labels for target-domain data and then exploit the predicted pseudo labels to fine-tune the segmentation model iteratively.…”

Section: Domain Adaptive Image Segmentationmentioning

confidence: 99%

Domain Adaptive Video Segmentation via Temporal Consistency Regularization

Guan¹,

Huang²,

Xiao³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Video semantic segmentation is an essential task for the analysis and understanding of videos. Recent efforts largely focus on supervised video segmentation by learning from fully annotated data, but the learnt models often experience clear performance drop while applied to videos of a different domain. This paper presents DA-VSN, a domain adaptive video segmentation network that addresses domain gaps in videos by temporal consistency regularization (TCR) for consecutive frames of target-domain videos. DA-VSN consists of two novel and complementary designs. The first is cross-domain TCR that guides the prediction of target frames to have similar temporal consistency as that of source frames (learnt from annotated source data) via adversarial learning. The second is intra-domain TCR that guides unconfident predictions of target frames to have similar temporal consistency as confident predictions of target frames. Extensive experiments demonstrate the superiority of our proposed domain adaptive video segmentation network which outperforms multiple baselines consistently by large margins.

show abstract

Scale variance minimization for unsupervised domain adaptation in image segmentation

Cited by 71 publications

References 33 publications

Aligning Correlation Information for Domain Adaptation in Action Recognition

Aligning Correlation Information for Domain Adaptation in Action Recognition

RDA: Robust Domain Adaptation via Fourier Adversarial Attacking

Domain Adaptive Video Segmentation via Temporal Consistency Regularization

Contact Info

Product

Resources

About