Meta-learning based relation and representation learning networks for single-image deraining

Gao, Xiao‐Zhi; Wang, Yang; Cheng, Jun; Xu, Mingliang; Wang, Meng

doi:10.1016/j.patcog.2021.108124

Cited by 18 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PDAG-Net [21] is the end-to-end progressive downsampling and adaptive guidance network to handle the shortcoming of existing downsampling methods. In the image deraining task, Gao et al [22] improve the deraining performance with a meta-learning based representation learning network. One of the generative and adversarial based approaches, DANet [23] applies the U-Net as the baseline of noise generator and denoiser.…”

Section: Related Work a Image Restorationmentioning

confidence: 99%

Decomformer: Decompose Self-Attention of Transformer for Efficient Image Restoration

Lee,

Hwang

2024

IEEE Access

View full text Add to dashboard Cite

A transformer architecture achieves outstanding performance in computer vision tasks based on the ability to capture long-range dependencies. However, a quadratic increase in complexity with respect to spatial resolution makes it impractical to apply for image restoration tasks. In this paper, we propose a Decomformer that efficiently captures global relationship by decomposing self-attention into linear combination of vectors and coefficients to reduce the heavy computational cost. This approximation not only reduces the complexity linearly, but also preserves the globality of the vanilla self-attention properly. Moreover, we apply a linear simple gate to represent the complex self-attention mechanism as the proposed decomposition directly. To show the effectiveness of our approach, we apply it to image restoration tasks including denoising, deblurring and deraining. The proposed decomposing scheme for self-attention in the Transformer achieves better or comparable results with state-of-the-arts as well as much more efficiency than most of previous approaches.

show abstract

Section: Related Work a Image Restorationmentioning

confidence: 99%

Decomformer: Decompose Self-Attention of Transformer for Efficient Image Restoration

Lee,

Hwang

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In Eqn. (27), the first and second expressions are the dichotomous and multiple classification expressions, respectively. In Eqn.…”

Section: Objective Functionmentioning

confidence: 99%

“…(34), the input is a triplet, including the anchoring example ( ), positive example ( ), and negative example ( ). Deng et al [27] use a triplet loss by optimizing the distance between the anchoring example and the positive example to be smaller than the distance between the anchoring example and the negative example, the similarity calculation between the samples is realized. In Eqn.…”

Section: Objective Functionmentioning

confidence: 99%

Data-Driven Single Image Deraining: A Comprehensive Review and New Perspectives

Zhang¹,

Yue²,

Zhang³

et al. 2023

Preprint

View full text Add to dashboard Cite

Single Image Deraining task aims at recovering the rain-free background from an image degraded by rain streaks and rain accumulation. For the powerful fitting ability of deep neural networks and massive training data, data-driven deep SID methods obtained significant improvement over traditional ones. Current SID methods usually focus on improving the deraining performance by proposing different kinds of deraining networks, while neglecting the interpretation of the solving process. As a result, the generalization ability may still be limited in real-world scenarios, and the deraining results also cannot effectively improve the performance of subsequent high-level tasks (e.g., object detection). To explore these issues, we in this paper re-examine the three important factors (i.e., data, rain model and network architecture) for the SID problem, and specifically analyze them by proposing new and more reasonable criteria (i.e., general vs. specific,synthetical vs. mathematical, black-box vs. white-box). We also study the relationship of the three factors from a new perspective of data, and reveal two different solving paradigms (explicit vs. implicit) for the SID task. We further discuss the current mainstream data-driven SID methods from five aspects, i.e., training strategy, network pipeline, domain knowledge, data preprocessing, and objective function, and some useful conclusions are summarized by statistics. Besides, we profoundly studied one of the three factors, i.e., data, and measured the performance of current methods on different datasets through extensive experiments to reveal the effectiveness of SID data. Finally, with the comprehensive review and in-depth analysis, we draw some valuable conclusions and suggestions for future research.

show abstract

“…The local linear embedding method describes the reconstruction relationship between local neighbor nodes with a graph, and maintains this local reconstruction relationship in a low-dimensional space. The Laplacian feature mapping method enables the latent low-dimensional space to still maintain the data similarity relationship in the original space, which is used to preserve the nonlinear structure of the data (Gao et al, 2021). However, when such methods are applied to large-scale networks, the computational complexity is greatly affected by the number of vertices, and the scalability is limited.…”

Section: Literature Reviewmentioning

confidence: 99%

Learning Behavior Evaluation Model and Teaching Strategy Innovation by Social Media Network Following Learning Psychology

Yuan

et al. 2022

Front. Psychol.

View full text Add to dashboard Cite

With the development of various network technologies and the spread of coronavirus disease 2019, many online learning platforms have been built. However, some of them may negatively impact student learning outcomes. Therefore, this study aims to improve the online learning effect of students by comprehensively evaluating their learning behavior by using deep learning algorithms. On this basis, new teaching strategies are proposed. According to the structured deep network embedding model, a network representation learning algorithm is proposed with the help of auto-encoders under deep learning. This study elaborates the concept and structure of the encoder model and tests its performance. After the node labels and dataset are trained, the applicable parameter λ2 of the model is 0.3. During the teaching process, the model’s reliability in distinguishing users is examined. Therefore, this model can be applied to network teaching, is an innovative teaching strategy, and provides a theoretical basis for improving teaching methods.

show abstract

Meta-learning based relation and representation learning networks for single-image deraining

Cited by 18 publications

References 23 publications

Decomformer: Decompose Self-Attention of Transformer for Efficient Image Restoration

Decomformer: Decompose Self-Attention of Transformer for Efficient Image Restoration

Data-Driven Single Image Deraining: A Comprehensive Review and New Perspectives

Learning Behavior Evaluation Model and Teaching Strategy Innovation by Social Media Network Following Learning Psychology

Contact Info

Product

Resources

About