Associative Domain Adaptation

Haeusser, Philip; Frerix, Thomas; Mordvintsev, Alexander; Cremers, Daniel

doi:10.48550/arxiv.1708.00938

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent relevant researches perform superior in visual recognition cross domain [30] [12] and task [34] and transfer structure learning [4] [21]. Besides of these two mainstreams, there are diverse methods to learn domain-invariant features: semisupervised method [42], domain reconstruction [14], duality [19], alignments [9] [50] [44], manifold learning [15], tensor methods [24][31], etc.…”

Section: Related Workmentioning

confidence: 99%

Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift

Xu¹,

Chen²,

Zuo³

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

342

333

View full text Add to dashboard Cite

Unsupervised domain adaptation (UDA) conventionally assumes labeled source samples coming from a single underlying source distribution. Whereas in practical scenario, labeled data are typically collected from diverse sources. The multiple sources are different not only from the target but also from each other, thus, domain adaptater should not be modeled in the same way. Moreover, those sources may not completely share their categories, which further brings a new transfer challenge called category shift. In this paper, we propose a deep cocktail network (DCTN) to battle the domain and category shifts among multiple sources. Motivated by the theoretical results in [33], the target distribution can be represented as the weighted combination of source distributions, and, the multi-source unsupervised domain adaptation via DCTN is then performed as two alternating steps: i) It deploys multi-way adversarial learning to minimize the discrepancy between the target and each of the multiple source domains, which also obtains the source-specific perplexity scores to denote the possibilities that a target sample belongs to different source domains. ii) The multi-source category classifiers are integrated with the perplexity scores to classify target sample, and the pseudolabeled target samples together with source samples are utilized to update the multi-source category classifier and the feature extractor. We evaluate DCTN in three domain adaptation benchmarks, which clearly demonstrate the superiority of our framework.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift

Xu¹,

Chen²,

Zuo³

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

342

333

View full text Add to dashboard Cite

show abstract

“…To facilitate learning cross-modal associations, we impose metric learning losses. This serves as a bootstrapping method which improves the cross-modal associations significantly compared to using either association learning [41] or metric learning [12] (ML) alone.…”

Section: Multimodal Metric Learningmentioning

confidence: 99%

Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings

Chen

Choy

Savva

et al. 2019

Computer Vision – ACCV 2018

106

View full text Add to dashboard Cite

We present a method for generating colored 3D shapes from natural language. To this end, we first learn joint embeddings of freeform text descriptions and colored 3D shapes. Our model combines and extends learning by association and metric learning approaches to learn implicit cross-modal connections, and produces a joint representation that captures the many-to-many relations between language and physical properties of 3D shapes such as color and shape. To evaluate our approach, we collect a large dataset of natural language descriptions for physical 3D objects in the ShapeNet dataset. With this learned joint embedding we demonstrate text-to-shape retrieval that outperforms baseline approaches. Using our embeddings with a novel conditional Wasserstein GAN framework, we generate colored 3D shapes from text. Our method is the first to connect natural language text with realistic 3D objects exhibiting rich variations in color, texture, and shape detail.

show abstract

Associative Domain Adaptation

Cited by 2 publications

References 0 publications

Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift

Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift

Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings

Contact Info

Product

Resources

About