Domain Adaptation for Structured Output via Discriminative Patch Representations

Tsai, Yi-Hsuan; Sohn, Kihyuk; Schulter, Samuel; Chandraker, Manmohan

doi:10.1109/iccv.2019.00154

Cited by 348 publications

(221 citation statements)

References 33 publications

Supporting

Mentioning

220

Contrasting

Order By: Relevance

“…[35] does the alignment on the prediction of the segmentation network and [39] proposes to do it on the weighted self-information of the prediction probability. [36] and [23] extend the approach of [35] by patch-level alignment and category-level adversarial loss respectively. Another use of adversarial training for UDA is proposed in [30,31], where the discrepancy between two instances of the same input from target domain is minimized while the classification layer tries to maximize it.…”

Section: Related Workmentioning

confidence: 99%

DADA: Depth-Aware Domain Adaptation in Semantic Segmentation

Jain

Bucher

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

184

147

View full text Add to dashboard Cite

Figure 1: We propose a novel depth-aware domain adaptation framework (DADA) to efficiently leverage depth as privileged information in the unsupervised domain adaptation setting. This example shows how semantic segmentation of a scene from the target domain benefits from the proposed approach, in comparison to state-of-the-art domain adaptation with no use of depth. In figure's top, we use different background colors (blue and red) to represent source and target information that are available during training. Here, annotated source domain data come from the synthetic SYNTHIA dataset and un-annotated target domain images are real scenes from Cityscapes. The cyclist highlighted by the yellow box is a good qualitative illustration of the improvement we obtain. AbstractUnsupervised domain adaptation (UDA) is important for applications where large scale annotation of representative data is challenging. For semantic segmentation in particular, it helps deploy, on real "target domain" data, models that are trained on annotated images from a different "source domain", notably a virtual environment. To this end, most previous works consider semantic segmentation as the only mode of supervision for source domain data, while ignoring other, possibly available, information like depth. In this work, we aim at exploiting at best such a privileged information while training the UDA model. We propose a unified depth-aware UDA framework that leverages in several complementary ways the knowledge of dense depth in the source domain. As a result, the performance of the trained semantic segmentation model on the target domain is boosted. Our novel approach indeed achieves state-of-the-art performance on different challenging synthetic-2-real benchmarks. Code and models are available at https://github.com/ valeoai/DADA.

show abstract

Section: Related Workmentioning

confidence: 99%

DADA: Depth-Aware Domain Adaptation in Semantic Segmentation

Jain

Bucher

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

184

147

View full text Add to dashboard Cite

show abstract

“…There has been notable recent interest in learning disentangled representations in various domains, such as computer vision [25], ML fairness [54,69], and domain adaptation [65,78], as they promise to enhance robustness, interpretability, and generalization to unseen examples on downstream tasks. The overall goal of disentangling is to improve the quality of the latent representations by explicitly separating the underlying factors of the observed data [38].…”

Section: Learning Disentangled Representationmentioning

confidence: 99%

Privacy-preserving Voice Analysis via Disentangled Representations

Aloufi

Haddadi

Boyle

2020

Proceedings of the 2020 ACM SIGSAC Conference on Cloud Computing Security Workshop

View full text Add to dashboard Cite

Voice User Interfaces (VUIs) are increasingly popular and built into smartphones, home assistants, and Internet of Things (IoT) devices. Despite offering an always-on convenient user experience, VUIs raise new security and privacy concerns for their users. In this paper, we focus on attribute inference attacks in the speech domain, demonstrating the potential for an attacker to accurately infer a target user's sensitive and private attributes (e.g. their emotion, sex, or health status) from deep acoustic models. To defend against this class of attacks, we design, implement, and evaluate a user-configurable, privacy-aware framework for optimizing speechrelated data sharing mechanisms. Our objective is to enable primary tasks such as speech recognition and user identification, while removing sensitive attributes in the raw speech data before sharing it with a cloud service provider. We leverage disentangled representation learning to explicitly learn independent factors in the raw data. Based on a user's preferences, a supervision signal informs the filtering out of invariant factors while retaining the factors reflected in the selected preference. Our experimental evaluation over five datasets shows that the proposed framework can effectively defend against attribute inference attacks by reducing their success rates to approximately that of guessing at random, while maintaining accuracy in excess of 99% for the tasks of interest. We conclude that negotiable privacy settings enabled by disentangled representations can bring new opportunities for privacy-preserving applications.

show abstract

“…[28] employed an adversarial learning scheme leveraging this property and achieved a significant performance improvement over previous methods. Recently, this work was extended to also leverage the more powerful local similarities by patch matching [29]. Curriculum Model Adaptation adapts models from an easier task to a harder task in a step-by-step fashion and has achieved great performance in multiple domain adaptation scenarios [34], [6], [5], [26].…”

Section: Domain Adaptationmentioning

confidence: 99%

Texture Underfitting for Domain Adaptation

Zaech

Dai

Hahner

et al. 2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

Comprehensive semantic segmentation is one of the key components for robust scene understanding and a requirement to enable autonomous driving. Driven by large scale datasets, convolutional neural networks show impressive results on this task. However, a segmentation algorithm generalizing to various scenes and conditions would require an enormously diverse dataset, making the labour intensive data acquisition and labeling process prohibitively expensive. Under the assumption of structural similarities between segmentation maps, domain adaptation promises to resolve this challenge by transferring knowledge from existing, potentially simulated datasets to new environments where no supervision exists. While the performance of this approach is contingent on the concept that neural networks learn a high level understanding of scene structure, recent work suggests that neural networks are biased towards overfitting to texture instead of learning structural and shape information. Considering the ideas underlying semantic segmentation, we employ random image stylization to augment the training dataset and propose a training procedure that facilitates texture underfitting to improve the performance of domain adaptation. In experiments with supervised as well as unsupervised methods for the task of synthetic-to-real domain adaptation, we show that our approach outperforms conventional training methods.

show abstract

Domain Adaptation for Structured Output via Discriminative Patch Representations

Cited by 348 publications

References 33 publications

DADA: Depth-Aware Domain Adaptation in Semantic Segmentation

DADA: Depth-Aware Domain Adaptation in Semantic Segmentation

Privacy-preserving Voice Analysis via Disentangled Representations

Texture Underfitting for Domain Adaptation

Contact Info

Product

Resources

About