Manifold discrimination partial adversarial domain adaptation

He, Chunmei; Zheng, Lanqing; Tan, Taifeng; Fan, Xianjun; Ye, Zhengchun

doi:10.1016/j.knosys.2022.109320

Cited by 10 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DCORAL embeds CORAL directly into a deep network, constructing a differentiable loss function to minimize cross-domain correlation differences. With the advent of Generative Adversarial Networks (GANs) [25], adversarial domain adaptation methods [26][27][28][29][30] have emerged, which aim to generate domain-transferable features through the adversarial game between a feature generator and a domain classifier. Inspired by the idea of GANs, a domain-adversarial neural network [31] is proposed, which involves three modules: a shared feature extractor cross-domain, a label classifier, and a domain classifier.…”

Section: Introductionmentioning

confidence: 99%

DJAN: Deep Joint Adaptation Network for Wildlife Image Recognition

Zhang,

Zhang

2023

Animals

View full text Add to dashboard Cite

Wildlife recognition is of utmost importance for monitoring and preserving biodiversity. In recent years, deep-learning-based methods for wildlife image recognition have exhibited remarkable performance on specific datasets and are becoming a mainstream research direction. However, wildlife image recognition tasks face the challenge of weak generalization in open environments. In this paper, a Deep Joint Adaptation Network (DJAN) for wildlife image recognition is proposed to deal with the above issue by taking a transfer learning paradigm into consideration. To alleviate the distribution discrepancy between the known dataset and the target task dataset while enhancing the transferability of the model’s generated features, we introduce a correlation alignment constraint and a strategy of conditional adversarial training, which enhance the capability of individual domain adaptation modules. In addition, a transformer unit is utilized to capture the long-range relationships between the local and global feature representations, which facilitates better understanding of the overall structure and relationships within the image. The proposed approach is evaluated on a wildlife dataset; a series of experimental results testify that the DJAN model yields state-of-the-art results, and, compared to the best results obtained by the baseline methods, the average accuracy of identifying the eleven wildlife species improves by 3.6 percentage points.

show abstract

Section: Introductionmentioning

confidence: 99%

DJAN: Deep Joint Adaptation Network for Wildlife Image Recognition

Zhang,

Zhang

2023

Animals

View full text Add to dashboard Cite

show abstract

“…Since the proposal of the first Variational AutoEncoder (VAE) [1], there have arisen numerous variations and enhancements for sophisticated issues such as time series modeling [2,3], finding latent information using deep hierarchical structures [4,5,6] or even dealing with heterogeneous and missing data [7,8].…”

Section: Introductionmentioning

confidence: 99%

Multimodal hierarchical Variational AutoEncoders with Factor Analysis latent space

Guerrero-López¹,

Sevilla-Salcedo²,

Gómez-Verdejo³

et al. 2022

Preprint

View full text Add to dashboard Cite

Real-world databases are complex, they usually present redundancy and shared correlations between heterogeneous and multiple representations of the same data. Thus, exploiting and disentangling shared information between views is critical. For this purpose, recent studies often fuse all views into a shared nonlinear complex latent space but they lose the interpretability. To overcome this limitation, here we propose a novel method to combine multiple Variational AutoEncoders (VAE) architectures with a Factor Analysis latent space (FA-VAE).Concretely, we use a VAE to learn a private representation of each heterogeneous view in a continuous latent space. Then, we model the shared latent space by projecting every private variable to a low-dimensional latent space using a linear projection matrix. Thus, we create an interpretable hierarchical dependency between private and shared information. This way, the novel model is able to simultaneously: (i) learn from multiple heterogeneous views, (ii) obtain an interpretable hierarchical shared space, and, (iii) perform transfer learning between generative models.

show abstract