Category-Level Adversarial Self-Ensembling for Domain Adaptation

Zuo, Yukun; Yao, Hantao; Xu, Changsheng

doi:10.1109/icme46284.2020.9102756

Cited by 6 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods based on self-ensembling usually incorporate adversarial training to further align the feature distributions of the source and target domains, or introduce consistency loss terms to promote the student network to learn consistent predictions across different perturbations of the input data. For instance, Zuo et al [ 16 ] proposed a category-level adversarial framework, which focuses on aligning the features of the source and target domains. In another recent work, Xu et al [ 17 ] designed a self-ensembling attention network to address domain shift, which is employed to promote the computation of consistency loss for the unlabeled domain.…”

Section: Introductionmentioning

confidence: 99%

Entropy and distance-guided super self-ensembling for optic disc and cup segmentation

He,

Kong,

et al. 2024

Biomed. Opt. Express

View full text Add to dashboard Cite

Segmenting the optic disc (OD) and optic cup (OC) is crucial to accurately detect changes in glaucoma progression in the elderly. Recently, various convolutional neural networks have emerged to deal with OD and OC segmentation. Due to the domain shift problem, achieving high-accuracy segmentation of OD and OC from different domain datasets remains highly challenging. Unsupervised domain adaptation has taken extensive focus as a way to address this problem. In this work, we propose a novel unsupervised domain adaptation method, called entropy and distance-guided super self-ensembling (EDSS), to enhance the segmentation performance of OD and OC. EDSS is comprised of two self-ensembling models, and the Gaussian noise is added to the weights of the whole network. Firstly, we design a super self-ensembling (SSE) framework, which can combine two self-ensembling to learn more discriminative information about images. Secondly, we propose a novel exponential moving average with Gaussian noise (G-EMA) to enhance the robustness of the self-ensembling framework. Thirdly, we propose an effective multi-information fusion strategy (MFS) to guide and improve the domain adaptation process. We evaluate the proposed EDSS on two public fundus image datasets RIGA+ and REFUGE. Large amounts of experimental results demonstrate that the proposed EDSS outperforms state-of-the-art segmentation methods with unsupervised domain adaptation, e.g., the Dicemean score on three test sub-datasets of RIGA+ are 0.8442, 0.8772 and 0.9006, respectively, and the Dicemean score on the REFUGE dataset is 0.9154.

show abstract

Section: Introductionmentioning

confidence: 99%

Entropy and distance-guided super self-ensembling for optic disc and cup segmentation

He,

Kong,

et al. 2024

Biomed. Opt. Express

View full text Add to dashboard Cite

show abstract

“…Meanwhile, according to the emotion theories [8,9], recent studies have considered both the theory-based sentiment composition and the spatial distribution considering class information in a latent feature space [10][11][12][13]. Secondly, researchers have concentrated on the small amount of well-labeled data [14][15][16][17][18][19][20][21][22]. Specifically, these methods regard a part of well-labeled data as unlabeled data.…”

Section: Introductionmentioning

confidence: 99%

“…the model has the ability to annotate sentiment labels [14][15][16][17]. Furthermore, to train with more than one dataset, domain adaptation (DA) approaches have been employed for image sentiment analysis [18][19][20][21][22].…”

Section: Introductionmentioning

confidence: 99%

Cross-Domain Semi-Supervised Deep Metric Learning for Image Sentiment Analysis

Liang

Maeda

Ogawa

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

This paper presents a novel method on image sentiment analysis called cross-domain semi-supervised deep metric learning (CDSS-DML). The proposed method has two contributions. Firstly, since previous researches on image sentiment analysis suffer from the limit of a small amount of well-labeled data, which occurs a decrease in accuracy of classification, CDSS-DML breaks through the limit by training with unlabeled data based on a teacher-student model. Secondly, the proposed method overcomes the difficulty of distribution shift between well-labeled and unlabeled data by jointing three losses. Especially, the proposed method constructs an effective latent space with the joint loss considering the inter-class and the intra-class correlations for image sentiments. From experimental results, the performance improvement with CDSS-DML is confirmed.

show abstract

Margin-Based Adversarial Joint Alignment Domain Adaptation

Zuo

Yao

Zhuang

et al. 2022

IEEE Trans. Circuits Syst. Video Technol.

Self Cite

View full text Add to dashboard Cite

Audio-visual video recognition (AVVR) aims to integrate audio and visual clues to categorize videos accurately. While existing methods train AVVR models using provided datasets and achieve satisfactory results, they struggle to retain historical class knowledge when confronted with new classes in real-world situations. Currently, there are no dedicated methods for addressing this problem, so this paper concentrates on exploring Class Incremental Audio-Visual Video Recognition (CIAVVR). For CIAVVR, since both stored data and learned model of past classes contain historical knowledge, the core challenge is how to capture past data knowledge and past model knowledge to prevent catastrophic forgetting. As audio-visual data and model inherently contain hierarchical structures, i.e., model embodies low-level and high-level semantic information, and data comprises snippet-level, video-level, and distribution-level spatial information, it is essential to fully exploit the hierarchical data structure for data knowledge preservation and hierarchical model structure for model knowledge preservation. However, current image class incremental learning methods do not explicitly consider these hierarchical structures in model and data. Consequently, we introduce Hierarchical Augmentation and Distillation (HAD), which comprises the Hierarchical Augmentation Module (HAM) and Hierarchical Distillation Module (HDM) to efficiently utilize the hierarchical structure of data and models, respectively. Specifically, HAM implements a novel augmentation strategy, segmental feature augmentation, to preserve hierarchical model knowledge. Meanwhile, HDM introduces newly designed hierarchical (video-distribution) logical distillation and hierarchical (snippet-video) correlative distillation to capture and maintain the hierarchical intra-sample knowledge of each data and the hierarchical inter-sample knowledge between data, respectively. Evaluations on four benchmarks (AVE, AVK-100, AVK-200, and AVK-400) demonstrate that the proposed HAD effectively captures hierarchical information in both data and models, resulting in better preservation of historical class knowledge and improved performance. Furthermore, we provide a theoretical analysis to support the necessity of the segmental feature augmentation strategy.

show abstract

Category-Level Adversarial Self-Ensembling for Domain Adaptation

Cited by 6 publications

References 16 publications

Entropy and distance-guided super self-ensembling for optic disc and cup segmentation

Entropy and distance-guided super self-ensembling for optic disc and cup segmentation

Cross-Domain Semi-Supervised Deep Metric Learning for Image Sentiment Analysis

Margin-Based Adversarial Joint Alignment Domain Adaptation

Contact Info

Product

Resources

About