Continual Image Deraining With Hypergraph Convolutional Networks

Fu, Xueyang; Xiao, Jie; Zhu, Yingjie; Liu, Aiping; Wu, Feng; Zha, Zheng-Jun

doi:10.1109/tpami.2023.3241756

Cited by 29 publications

(12 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several common connection methods are utilized in neural networks, such as fully connected networks, recurrent networks, and convolutional networks. [110][111][112] Following the establishment of these connections, synaptic weights are assigned and regulated using either analog circuits or digital logic circuits. During the mapping process of a neural network, meticulous attention must be given to several crucial factors, such as several key factors, such as the topology of the neural network and the rational allocation of resources.…”

Section: Design Of Neural Networkmentioning

confidence: 99%

Memristor‐Based Neuromorphic Chips

Duan,

Cao,

Gao

et al. 2024

Advanced Materials

View full text Add to dashboard Cite

In the era of information, characterized by an exponential growth in data volume and an escalating level of data abstraction, there has been a substantial focus on brain‐like chips, which are known for their robust processing power and energy‐efficient operation. Memristors are widely acknowledged as the optimal electronic devices for the realization of neuromorphic computing, due to their innate ability to emulate the interconnection and information transfer processes witnessed among neurons. This review paper focuses on memristor‐based neuromorphic chips, which provide an extensive description of the working principle and characteristic features of memristors, along with their applications in the realm of neuromorphic chips. Subsequently, a thorough discussion of the memristor array, which serves as the pivotal component of the neuromorphic chip, as well as an examination of the present mainstream neural networks, is delved. Furthermore, the design of the neuromorphic chip is categorized into three crucial sections, including synapse‐neuron cores, networks on chip (NoC), and neural network design. Finally, the key performance metrics of the chip is highlighted, as well as the key metrics related to the memristor devices are employed to realize both the synaptic and neuronal components.

show abstract

Section: Design Of Neural Networkmentioning

confidence: 99%

Memristor‐Based Neuromorphic Chips

Duan,

Cao,

Gao

et al. 2024

Advanced Materials

View full text Add to dashboard Cite

show abstract

“…Drawing on the concept of closedloop control, Li et al [69] designed a robust representation learning network structure by incorporating feedback mechanism into the CNN. Recently, Fu et al [10] developed a patch-wise hypergraph convolutional network architecture to help the model to explore non-local content of the images.…”

Section: Network Architecturesmentioning

confidence: 99%

“…In this track, multiple pretrained models are obtained to evaluate the corresponding testing sets, including Rain200L [8], Rain200H [8], DID-Data [36], DDN-Data [35], and SPA-Data [15]. Here, we provide 22 representative methods in Table 6, i.e., DDN [35], DID-MDN [36], RESCAN [38], NLEDN [39], JORDER-E [53], ID-CGAN [48], SIRR [45], PReNet [42], SPANet [15], FBL [62], MSPFN [18], RCDNet [57], Syn2Real [58], SGCN [104], MPRNet [19], DualGCN [13], SPDNet [12], Uformer [81], Restormer [20], IDT [11], HCN [10], and DRSformer [9]. The quantitative results are quoted from previous works [9], [10].…”

Section: Evaluation On Independent Training Trackmentioning

confidence: 99%

“…Here, we provide 22 representative methods in Table 6, i.e., DDN [35], DID-MDN [36], RESCAN [38], NLEDN [39], JORDER-E [53], ID-CGAN [48], SIRR [45], PReNet [42], SPANet [15], FBL [62], MSPFN [18], RCDNet [57], Syn2Real [58], SGCN [104], MPRNet [19], DualGCN [13], SPDNet [12], Uformer [81], Restormer [20], IDT [11], HCN [10], and DRSformer [9]. The quantitative results are quoted from previous works [9], [10]. Each method is evaluated under the same implementation using PSNR [21] and SSIM [117].…”

Section: Evaluation On Independent Training Trackmentioning

confidence: 99%

“…There exist several classical synthetic datasets for single image deraining task, such as the Rain100L [8], Rain100H [8], and Rain800 [5]. Although these synthetic datasets are prevalent in current studies [9], [10], [11], [12], [13], [14], most approaches randomly add rain effects to any clear backgrounds to build the synthetic paired data, which inevitably leads to inadequate realism and harmony, especially in the sky region (see Figure 1(a)). As a result, there is a large domain gap between synthetic and real data, which limits the ability of training better deep deraining models.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Unpaired Deep Image Deraining Using Dual Contrastive Learning

Chen

Pan

Jiang

et al. 2022

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

131

View full text Add to dashboard Cite

Recent years have witnessed significant advances in image deraining due to the kinds of effective image priors and deep learning models. As each deraining approach has individual settings (e.g., training and test datasets, evaluation criteria), how to fairly evaluate existing approaches comprehensively is not a trivial task. Although existing surveys aim to review of image deraining approaches comprehensively, few of them focus on providing unify evaluation settings to examine the deraining capability and practicality evaluation. In this paper, we provide a comprehensive review of existing image deraining method and provide a unify evaluation setting to evaluate the performance of image deraining methods. We construct a new high-quality benchmark named HQ-RAIN to further conduct extensive evaluation, consisting of 5,000 paired high-resolution synthetic images with higher harmony and realism. We also discuss the existing challenges and highlight several future research opportunities worth exploring. To facilitate the reproduction and tracking of the latest deraining technologies for general users, we build an online platform to provide the off-the-shelf toolkit, involving the large-scale performance evaluation. This online platform and the proposed new benchmark are publicly available and will be regularly updated at http://www.deraining.tech/.

show abstract

OneRestore: A Universal Restoration Framework for Composite Degradation

Guo,

Gao,

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Continual Image Deraining With Hypergraph Convolutional Networks

Cited by 29 publications

References 84 publications

Memristor‐Based Neuromorphic Chips

Memristor‐Based Neuromorphic Chips

Unpaired Deep Image Deraining Using Dual Contrastive Learning

OneRestore: A Universal Restoration Framework for Composite Degradation

Contact Info

Product

Resources

About