Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings

Prabhu, Viraj; Chandrasekaran, Arjun; Saenko, Kate; Hoffman, Judy

doi:10.1109/iccv48922.2021.00839

Cited by 91 publications

(46 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Active domain adaptation has since been extended to deep learning [48,38]. The querying strategies range from those based on clustering [30] to margins of classifiers. Batch query methods are also proposed in [29,23].…”

Section: Active Domain Adaptationmentioning

confidence: 99%

Cost-effective Framework for Gradual Domain Adaptation with Multifidelity

Sagawa¹,

Hino²

2022

Preprint

View full text Add to dashboard Cite

In domain adaptation, when there is a large distance between the source and target domains, the prediction performance will degrade. Gradual domain adaptation is one of the solutions to such an issue, assuming that we have access to intermediate domains, which shift gradually from the source to target domains. In previous works, it was assumed that the number of samples in the intermediate domains is sufficiently large; hence, self-training was possible without the need for labeled data. If access to an intermediate domain is restricted, self-training will fail. Practically, the cost of samples in intermediate domains will vary, and it is natural to consider that the closer an intermediate domain is to the target domain, the higher the cost of obtaining samples from the intermediate domain is. To solve the trade-off between cost and accuracy, we propose a framework that combines multifidelity and active domain adaptation. The effectiveness of the proposed method is evaluated by experiments with both artificial and real-world datasets. Codes are available at https://github.com/ssgw320/gdamf.

show abstract

Section: Active Domain Adaptationmentioning

confidence: 99%

Cost-effective Framework for Gradual Domain Adaptation with Multifidelity

Sagawa¹,

Hino²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Without a further discussion of which samples can be saved in the buffer, we find this method limited in the exercise of the right to be forgotten. Active Domain Adaptation [6,11,47,49,61,64,66,70] also benefits the online learning of shifting domains. It bears a different setting: the target domain can actively acquire labeled data online.…”

Section: Related Workmentioning

confidence: 99%

Burn After Reading: Online Adaptation for Cross-domain Streaming Data

Yang¹,

Gao²,

Chen³

et al. 2021

Preprint

View full text Add to dashboard Cite

In the context of online privacy, many methods propose complex privacy and security preserving measures to protect sensitive data. In this paper we argue that: not storing any sensitive data is the best form of security. Thus we propose an online framework that "burns after reading", i.e. each online sample is immediately deleted after it is processed. Meanwhile, we tackle the inevitable distribution shift between the labeled public data and unlabeled private data as a problem of unsupervised domain adaptation. Specifically, we propose a novel algorithm that aims at the most fundamental challenge of the online adaptation setting-the lack of diverse source-target data pairs. Therefore, we design a Cross-Domain Bootstrapping approach, called CRODOBO, to increase the combined diversity across domains. Further, to fully exploit the valuable discrepancies among the diverse combinations, we employ the training strategy of multiple learners with cosupervision. CRODOBO achieves state-of-the-art online performance on four domain adaptation benchmarks.

show abstract

Section: Active Domain Adaptation (Ada)mentioning

confidence: 99%

“…Existing works mainly focus on image classification task [12,[43][44][45]60]. To name a few, Prabhu et al [43] combine the uncertainty and diversity into an acquisition round and integrate semi-supervised domain adaptation into a unified framework. Lately, Ning et al [40] and Shin et al [53] are among the first to study the task of ADA applied to semantic segmentation, which greatly enhances the segmentation performance on the target domain.…”

Section: Active Domain Adaptation (Ada)mentioning

confidence: 99%

Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation

Xie¹,

Yuan²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

Self-training has greatly facilitated domain adaptive semantic segmentation, which iteratively generates pseudo labels on the target domain and retrains the network. However, since the realistic segmentation datasets are highly imbalanced, target pseudo labels are typically biased to the majority classes and basically noisy, leading to an errorprone and sub-optimal model. To address this issue, we propose a region-based active learning approach for semantic segmentation under a domain shift, aiming to automatically query a small partition of image regions to be labeled while maximizing segmentation performance. Our algorithm, Active Learning via Region Impurity and Prediction Uncertainty (AL-RIPU), introduces a novel acquisition strategy characterizing the spatial adjacency of image regions along with the prediction confidence. We show that the proposed region-based selection strategy makes more efficient use of a limited budget than image-based or pointbased counterparts. Meanwhile, we enforce local prediction consistency between a pixel and its nearest neighbor on a source image. Further, we develop a negative learning loss to enhance the discriminative representation learning on the target domain. Extensive experiments demonstrate that our method only requires very few annotations to almost reach the supervised performance and substantially outperforms state-of-the-art methods.* Corresponding author (a) Target image (b) Image-based selection (100%) (c) Point-based selection (2.2%) (d) Region-based selection (2.2%)

show abstract

Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings

Cited by 91 publications

References 18 publications

Cost-effective Framework for Gradual Domain Adaptation with Multifidelity

Cost-effective Framework for Gradual Domain Adaptation with Multifidelity

Burn After Reading: Online Adaptation for Cross-domain Streaming Data

Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation

Contact Info

Product

Resources

About