Domain Adaptive Ensemble Learning

By Kaiyang Zhou, Yongxin Yang, Yu Qiao, Tao A. Xiang. IEEE Transactions on Image Processing, 2020

366 citations recorded by the source corpus.

The problem of generalizing deep neural networks from multiple source domains to a target one is studied under two settings: When unlabeled target data is available, it is a multi-source unsupervised domain adaptation (UDA) problem, otherwise a domain generalization (DG) problem. We propose a unified framework termed domain adaptive ensemble learning (DAEL) to address both problems. A DAEL model is composed of a CNN feature extractor shared across domains and multiple classifier heads each trained to specialize in a particular source domain. Each such classifier is an expert to its own domain but a non-expert to others. DAEL aims to learn these experts collaboratively so that when forming an ensemble, they can leverage complementary information from each other to be more effective for an unseen target domain. To this end, each source domain is used in turn as a pseudo-target-domain with its own expert providing supervisory signal to the ensemble of non-experts learned from the other sources. To deal with unlabeled target data under the UDA setting where real expert does not exist, DAEL uses pseudo labels to supervise the ensemble learning. Extensive experiments on three multi-source UDA datasets and two DG datasets show that DAEL improves the state of the art on both problems, often by significant margins.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/1f49f005859e966af8d8fcfb2ec3e880e5afde94

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Generalizing to Unseen Domains: A Survey on Domain Generalization (2021, background): “learning is a kind of multi-task learning, which trains on multiple related domains to learn good models for each original domain [8] instead of new test domains.”
Domain Generalization: A Survey (2021, neutral): “Object recognition - VLCS [56] 10,729 4 Caltech101 [44], LabelMe [45], PASCAL [57], SUN09 [58] - Office-31 [12] 4,652 3 Amazon, webcam, dslr - OfficeHome [59] 15,588 4 Art, clipart, product, real - PACS [37] 9,991 4 Photo, art, cartoon, sketch - DomainNet [60] 586,575 6 Clipart, infograph, painting,”
Domain Generalization with MixStyle (2021, methodology): “Whereas L2A-OT works at the pixel level: it trains an image generator by maximizing the domain difference (measured by optimal transport) between the original and the generated images, which introduces much heavier computational overhead than MixStyle in terms of GPU memory and training time.”
Learning to Generate Novel Domains for Domain Generalization (2020, positive): “Our implementation is based on Dassl.pytorch [63].”