Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation

Wang, Zhonghao; Yu, Mo; Wei, Yunchao; Feris, Rogério; Xiong, Jinjun; Hwu, Wen-mei W.; Huang, Thomas S.

doi:10.48550/arxiv.2003.08040

Cited by 8 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, the model F could be for semantic segmentation, object detection or image classification task. The data could be labeled source data with supervised source losses or unlabeled target data with unsupervised target losses such as adversarial loss [81,52,86,93,58,46,32,70], self-training loss [104,103,45,88,40,94] or entropy loss [86,18], etc. Below are a supervised loss and a self-training-based unsupervised loss here for reference:…”

Section: Robust Domain Adaptationmentioning

confidence: 99%

RDA: Robust Domain Adaptation via Fourier Adversarial Attacking

Huang

Guan

Xiao

et al. 2021

Preprint

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

Section: Robust Domain Adaptationmentioning

confidence: 99%

RDA: Robust Domain Adaptation via Fourier Adversarial Attacking

Huang

Guan

Xiao

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…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

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

“…[72], entropy space [77], patch space [73], and context space [33]. They can also be learnt through sample or class joint AT [47,79], multi-level AT [63], regularized AT [83], or intra-domain AT [52].…”

Section: Introductionmentioning

confidence: 99%

Category Contrast for Unsupervised Domain Adaptation in Visual Tasks

Huang¹,

Guan²,

Xiao³

et al. 2021

Preprint

View full text Add to dashboard Cite

Instance contrast for unsupervised representation learning has achieved great success in recent years. In this work, we explore the idea of instance contrastive learning in unsupervised domain adaptation (UDA) and propose a novel Category Contrast technique (CaCo) that introduces semantic priors on top of instance discrimination for visual UDA tasks. By considering instance contrastive learning as a dictionary look-up operation, we construct a semantics-aware dictionary with samples from both source and target domains where each target sample is assigned a (pseudo) category label based on the category priors of source samples. This allows category contrastive learning (between target queries and the category-level dictionary) for category-discriminative yet domain-invariant feature representations: samples of the same category (from either source or target domain) are pulled closer while those of different categories are pushed apart simultaneously. Extensive UDA experiments in multiple visual tasks (e.g., segmentation, classification and detection) show that the simple implementation of CaCo achieves superior performance as compared with the highly-optimized state-of-the-art methods. Analytically and empirically, the experiments also demonstrate that CaCo is complementary to existing UDA methods and generalizable to other learning setups such as semi-supervised learning, unsupervised model adaptation, etc.

show abstract

Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation

Cited by 8 publications

References 35 publications

RDA: Robust Domain Adaptation via Fourier Adversarial Attacking

RDA: Robust Domain Adaptation via Fourier Adversarial Attacking

Domain Adaptive Video Segmentation via Temporal Consistency Regularization

Category Contrast for Unsupervised Domain Adaptation in Visual Tasks

Contact Info

Product

Resources

About