最近的卷积神经网络(CNN)的改进 - 基于单图像超分辨率(SISR)方法严重依赖于制造网络架构,而不是发现除了简单地降低回归损耗之外的合适的培训算法。调整知识蒸馏(KD)可以开辟一种方法,以便对SISR进行进一步改进,并且在模型效率方面也是有益的。 KD是一种模型压缩方法,可提高深神经网络(DNN)的性能而不使用其他参数进行测试。它最近越来越敏捷,以提供更好的能力性能权衡。在本文中,我们提出了一种适用于SISR的新型特征蒸馏(FD)方法。我们展示了基于FITNET的FD方法的局限性,它在SISR任务中受到影响,并建议修改现有的FD算法以专注于本地特征信息。此外,我们提出了一种基于教师 - 学生差异的软特征注意方法,其选择性地专注于特定的像素位置以提取特征信息。我们致电我们的方法本地选择性特征蒸馏(LSFD)并验证我们的方法在SISR问题中优于传统的FD方法。
translated by 谷歌翻译
Convolution Neural Networks (CNNs) have been used in various fields and are showing demonstrated excellent performance, especially in Single-Image Super Resolution (SISR). However, recently, CNN-based SISR has numerous parameters and computational costs for obtaining better performance. As one of the methods to make the network efficient, Knowledge Distillation (KD) which optimizes the performance trade-off by adding a loss term to the existing network architecture is currently being studied. KD for SISR is mainly proposed as a feature distillation (FD) to minimize L1-distance loss of feature maps between teacher and student networks, but it does not fully take into account the amount and importance of information that the student can accept. In this paper, we propose a feature-based adaptive contrastive distillation (FACD) method for efficiently training lightweight SISR networks. We show the limitations of the existing feature-distillation (FD) with L1-distance loss, and propose a feature-based contrastive loss that maximizes the mutual information between the feature maps of the teacher and student networks. The experimental results show that the proposed FACD improves not only the PSNR performance of the entire benchmark datasets and scales but also the subjective image quality compared to the conventional FD approach.
translated by 谷歌翻译
知识蒸馏(KD)可以有效地将知识从繁琐的网络(教师)转移到紧凑的网络(学生),在某些计算机视觉应用中证明了其优势。知识的表示对于知识转移和学生学习至关重要,这通常以手工制作的方式定义或直接使用中间功能。在本文中,我们建议在教师学生架构下为单像超级分辨率任务提出一种模型 - 不足的元知识蒸馏方法。它提供了一种更灵活,更准确的方法,可以通过知识代表网络(KRNET)的能力来帮助教师通过具有可学习参数的知识传输知识。为了提高知识表示对学生需求的看法能力,我们建议通过采用学生特征以及KRNET中的教师和学生之间的相关性来解决从中间产出到转移知识的转型过程。具体而言,生成纹理感知的动态内核,然后提取要改进的纹理特征,并将相应的教师指导分解为质地监督,以进一步促进高频细节的恢复质量。此外,KRNET以元学习方式进行了优化,以确保知识转移和学生学习有益于提高学生的重建质量。在各种单个图像超分辨率数据集上进行的实验表明,我们所提出的方法优于现有的定义知识表示相关的蒸馏方法,并且可以帮助超分辨率算法实现更好的重建质量,而无需引入任何推理复杂性。
translated by 谷歌翻译
深度学习的巨大成功主要是由于大规模的网络架构和高质量的培训数据。但是,在具有有限的内存和成像能力的便携式设备上部署最近的深层模型仍然挑战。一些现有的作品通过知识蒸馏进行了压缩模型。不幸的是,这些方法不能处理具有缩小图像质量的图像,例如低分辨率(LR)图像。为此,我们采取了开创性的努力,从高分辨率(HR)图像到达将处理LR图像的紧凑型网络模型中学习的繁重网络模型中蒸馏有用的知识,从而推动了新颖的像素蒸馏的当前知识蒸馏技术。为实现这一目标,我们提出了一名教师助理 - 学生(TAS)框架,将知识蒸馏分解为模型压缩阶段和高分辨率表示转移阶段。通过装备新颖的特点超分辨率(FSR)模块,我们的方法可以学习轻量级网络模型,可以实现与重型教师模型相似的准确性,但参数更少,推理速度和较低分辨率的输入。在三个广泛使用的基准,\即,幼崽200-2011,Pascal VOC 2007和ImageNetsub上的综合实验证明了我们方法的有效性。
translated by 谷歌翻译
Informative features play a crucial role in the single image super-resolution task. Channel attention has been demonstrated to be effective for preserving information-rich features in each layer. However, channel attention treats each convolution layer as a separate process that misses the correlation among different layers. To address this problem, we propose a new holistic attention network (HAN), which consists of a layer attention module (LAM) and a channel-spatial attention module (CSAM), to model the holistic interdependencies among layers, channels, and positions. Specifically, the proposed LAM adaptively emphasizes hierarchical features by considering correlations among layers. Meanwhile, CSAM learns the confidence at all the positions of each channel to selectively capture more informative features. Extensive experiments demonstrate that the proposed HAN performs favorably against the state-ofthe-art single image super-resolution approaches.
translated by 谷歌翻译
Recently, deep convolutional neural networks (CNNs) have been widely explored in single image super-resolution (SISR) and obtained remarkable performance. However, most of the existing CNN-based SISR methods mainly focus on wider or deeper architecture design, neglecting to explore the feature correlations of intermediate layers, hence hindering the representational power of CNNs. To address this issue, in this paper, we propose a second-order attention network (SAN) for more powerful feature expression and feature correlation learning. Specifically, a novel trainable second-order channel attention (SOCA) module is developed to adaptively rescale the channel-wise features by using second-order feature statistics for more discriminative representations. Furthermore, we present a non-locally enhanced residual group (NLRG) structure, which not only incorporates non-local operations to capture long-distance spatial contextual information, but also contains repeated local-source residual attention groups (LSRAG) to learn increasingly abstract feature representations. Experimental results demonstrate the superiority of our SAN network over state-of-the-art SISR methods in terms of both quantitative metrics and visual quality.
translated by 谷歌翻译
基于变压器的方法与基于CNN的方法相比,由于其对远程依赖性的模型,因此获得了令人印象深刻的图像恢复性能。但是,像Swinir这样的进步采用了基于窗口的和本地注意力的策略来平衡性能和计算开销,这限制了采用大型接收领域来捕获全球信息并在早期层中建立长期依赖性。为了进一步提高捕获全球信息的效率,在这项工作中,我们建议Swinfir通过更换具有整个图像范围的接收场的快速傅立叶卷积(FFC)组件来扩展Swinir。我们还重新访问其他先进技术,即数据增强,预训练和功能集合,以改善图像重建的效果。并且我们的功能合奏方法使模型的性能得以大大增强,而无需增加训练和测试时间。与现有方法相比,我们将算法应用于多个流行的大规模基准,并实现了最先进的性能。例如,我们的Swinfir在漫画109数据集上达到了32.83 dB的PSNR,该PSNR比最先进的Swinir方法高0.8 dB。
translated by 谷歌翻译
随着深度学习(DL)的出现,超分辨率(SR)也已成为一个蓬勃发展的研究领域。然而,尽管结果有希望,但该领域仍然面临需要进一步研究的挑战,例如,允许灵活地采样,更有效的损失功能和更好的评估指标。我们根据最近的进步来回顾SR的域,并检查最新模型,例如扩散(DDPM)和基于变压器的SR模型。我们对SR中使用的当代策略进行了批判性讨论,并确定了有前途但未开发的研究方向。我们通过纳入该领域的最新发展,例如不确定性驱动的损失,小波网络,神经体系结构搜索,新颖的归一化方法和最新评估技术来补充先前的调查。我们还为整章中的模型和方法提供了几种可视化,以促进对该领域趋势的全球理解。最终,这篇综述旨在帮助研究人员推动DL应用于SR的界限。
translated by 谷歌翻译
基于深度学习的单图像超分辨率(SISR)方法引起了人们的关注,并在现代高级GPU上取得了巨大的成功。但是,大多数最先进的方法都需要大量参数,记忆和计算资源,这些参数通常会显示在当前移动设备CPU/NPU上时显示出较低的推理时间。在本文中,我们提出了一个简单的普通卷积网络,该网络具有快速最近的卷积模块(NCNET),该模块对NPU友好,可以实时执行可靠的超级分辨率。提出的最近的卷积具有与最近的UP采样相同的性能,但更快,更适合Android NNAPI。我们的模型可以很容易地在具有8位量化的移动设备上部署,并且与所有主要的移动AI加速器完全兼容。此外,我们对移动设备上的不同张量操作进行了全面的实验,以说明网络体系结构的效率。我们的NCNET在DIV2K 3X数据集上进行了训练和验证,并且与其他有效的SR方法的比较表明,NCNET可以实现高保真SR结果,同时使用更少的推理时间。我们的代码和预估计的模型可在\ url {https://github.com/algolzw/ncnet}上公开获得。
translated by 谷歌翻译
卷积神经网络在过去十年中允许在单个图像超分辨率(SISR)中的显着进展。在SISR最近的进展中,关注机制对于高性能SR模型至关重要。但是,注意机制仍然不清楚为什么它在SISR中的工作原理。在这项工作中,我们试图量化和可视化SISR中的注意力机制,并表明并非所有关注模块都同样有益。然后,我们提出了关注网络(A $ ^ 2 $ n)的注意力,以获得更高效和准确的SISR。具体来说,$ ^ 2 $ n包括非关注分支和耦合注意力分支。提出了一种动态注意力模块,为这两个分支产生权重,以动态地抑制不需要的注意力调整,其中权重根据输入特征自适应地改变。这允许注意模块专门从事惩罚的有益实例,从而大大提高了注意力网络的能力,即几个参数开销。实验结果表明,我们的最终模型A $ ^ 2 $ n可以实现与类似尺寸的最先进网络相比的卓越的权衡性能。代码可以在https://github.com/haoyuc/a2n获得。
translated by 谷歌翻译
Recent research on super-resolution has progressed with the development of deep convolutional neural networks (DCNN). In particular, residual learning techniques exhibit improved performance. In this paper, we develop an enhanced deep super-resolution network (EDSR) with performance exceeding those of current state-of-the-art SR methods. The significant performance improvement of our model is due to optimization by removing unnecessary modules in conventional residual networks. The performance is further improved by expanding the model size while we stabilize the training procedure. We also propose a new multi-scale deep super-resolution system (MDSR) and training method, which can reconstruct high-resolution images of different upscaling factors in a single model. The proposed methods show superior performance over the state-of-the-art methods on benchmark datasets and prove its excellence by winning the NTIRE2017 Super-Resolution Challenge [26].
translated by 谷歌翻译
单个图像超分辨率(SISR)是一个不良问题,旨在获得从低分辨率(LR)输入的高分辨率(HR)输出,在此期间应该添加额外的高频信息以改善感知质量。现有的SISR工作主要通过最小化平均平方重建误差来在空间域中运行。尽管高峰峰值信噪比(PSNR)结果,但难以确定模型是否正确地添加所需的高频细节。提出了一些基于基于残余的结构,以指导模型暗示高频率特征。然而,由于空间域度量的解释是有限的,如何验证这些人为细节的保真度仍然是一个问题。在本文中,我们提出了频率域视角来的直观管道,解决了这个问题。由现有频域的工作启发,我们将图像转换为离散余弦变换(DCT)块,然后改革它们以获取DCT功能映射,它用作我们模型的输入和目标。设计了专门的管道,我们进一步提出了符合频域任务的性质的频率损失功能。我们的SISR方法在频域中可以明确地学习高频信息,为SR图像提供保真度和良好的感知质量。我们进一步观察到我们的模型可以与其他空间超分辨率模型合并,以提高原始SR输出的质量。
translated by 谷歌翻译
Image super-resolution (SR) serves as a fundamental tool for the processing and transmission of multimedia data. Recently, Transformer-based models have achieved competitive performances in image SR. They divide images into fixed-size patches and apply self-attention on these patches to model long-range dependencies among pixels. However, this architecture design is originated for high-level vision tasks, which lacks design guideline from SR knowledge. In this paper, we aim to design a new attention block whose insights are from the interpretation of Local Attribution Map (LAM) for SR networks. Specifically, LAM presents a hierarchical importance map where the most important pixels are located in a fine area of a patch and some less important pixels are spread in a coarse area of the whole image. To access pixels in the coarse area, instead of using a very large patch size, we propose a lightweight Global Pixel Access (GPA) module that applies cross-attention with the most similar patch in an image. In the fine area, we use an Intra-Patch Self-Attention (IPSA) module to model long-range pixel dependencies in a local patch, and then a $3\times3$ convolution is applied to process the finest details. In addition, a Cascaded Patch Division (CPD) strategy is proposed to enhance perceptual quality of recovered images. Extensive experiments suggest that our method outperforms state-of-the-art lightweight SR methods by a large margin. Code is available at https://github.com/passerer/HPINet.
translated by 谷歌翻译
Convolutional neural network (CNN) depth is of crucial importance for image super-resolution (SR). However, we observe that deeper networks for image SR are more difficult to train. The lowresolution inputs and features contain abundant low-frequency information, which is treated equally across channels, hence hindering the representational ability of CNNs. To solve these problems, we propose the very deep residual channel attention networks (RCAN). Specifically, we propose a residual in residual (RIR) structure to form very deep network, which consists of several residual groups with long skip connections. Each residual group contains some residual blocks with short skip connections. Meanwhile, RIR allows abundant low-frequency information to be bypassed through multiple skip connections, making the main network focus on learning high-frequency information. Furthermore, we propose a channel attention mechanism to adaptively rescale channel-wise features by considering interdependencies among channels. Extensive experiments show that our RCAN achieves better accuracy and visual improvements against state-of-the-art methods.
translated by 谷歌翻译
深度学习取得了面部识别基准的出色性能,但是对于低分辨率(LR)图像,性能大大降低了。我们提出了一种注意力相似性知识蒸馏方法,该方法将作为教师的高分辨率(HR)网络获得的注意图转移到LR网络中,以提高LR识别性能。受到人类能够基于从HR图像获得的先验知识近似物体区域的人类的启发,我们设计了使用余弦相似性的知识蒸馏损失,以使学生网络的注意力类似于教师网络的注意力。在各种LR面部相关的基准上进行的实验证实了所提出的方法通常改善了LR设置上的识别性能,通过简单地传输良好的注意力图来优于最先进的结果。 https://github.com/gist-ailab/teaching-where-where-to-look在https://github.com/github.com/github.com/phis-look中公开可用。
translated by 谷歌翻译
已经证明了深度卷积神经网络近年来对SISR有效。一方面,已经广泛使用了残余连接和密集连接,以便于前向信息和向后梯度流动以提高性能。然而,当前方法以次优的方式在大多数网络层中单独使用残留连接和密集连接。另一方面,虽然各种网络和方法旨在改善计算效率,节省参数或利用彼此的多种比例因子的训练数据来提升性能,但它可以在人力资源空间中进行超级分辨率来具有高计算成本或不能在不同尺度因子的模型之间共享参数以节省参数和推理时间。为了解决这些挑战,我们提出了一种使用双路径连接的高效单图像超分辨率网络,其多种规模学习命名为EMSRDPN。通过将双路径的双路径连接引入EMSRDPN,它在大多数网络层中以综合方式使用残差连接和密集连接。双路径连接具有重用残余连接的共同特征和探索密集连接的新功能,以了解SISR的良好代表。要利用多种比例因子的特征相关性,EMSRDPN在不同缩放因子之间共享LR空间中的所有网络单元,以学习共享功能,并且仅使用单独的重建单元进行每个比例因子,这可以利用多种规模因子的培训数据来帮助各个规模因素另外提高性能,同时可以节省参数并支持共享推理,以提高效率的多种规模因素。实验显示EMSRDPN通过SOTA方法实现更好的性能和比较或更好的参数和推理效率。
translated by 谷歌翻译
作为一个严重的问题,近年来已经广泛研究了单图超分辨率(SISR)。 SISR的主要任务是恢复由退化程序引起的信息损失。根据Nyquist抽样理论,降解会导致混叠效应,并使低分辨率(LR)图像的正确纹理很难恢复。实际上,自然图像中相邻斑块之间存在相关性和自相似性。本文考虑了自相似性,并提出了一个分层图像超分辨率网络(HSRNET)来抑制混叠的影响。我们从优化的角度考虑SISR问题,并根据半季节分裂(HQS)方法提出了迭代解决方案模式。为了先验探索本地图像的质地,我们设计了一个分层探索块(HEB)并进行性增加了接受场。此外,设计多级空间注意力(MSA)是为了获得相邻特征的关系并增强了高频信息,这是视觉体验的关键作用。实验结果表明,与其他作品相比,HSRNET实现了更好的定量和视觉性能,并更有效地释放了别名。
translated by 谷歌翻译
最近,基于深度学习的超分辨率方法取得了良好的性能,但主要关注通过喂养许多样品来训练单个广义的深网络。但是直观地,每个图像都具有其表示,并且预计将获得自适应模型。对于此问题,我们通过利用图像或特征的全局上下文信息来提出一种新颖的图像特异性卷积核调制(IKM),以产生适当地调制卷积核的注意重量,这越优于Vanilla卷积和几个现有的注意机制在没有任何其他参数的情况下嵌入最先进的架构。特别是,为了优化我们在迷你批量培训中的IKM,我们引入了一种特定于图像的优化(ISO)算法,比传统的迷你批量SGD优化更有效。此外,我们调查IKM对最先进的架构的影响,并利用一个带有U风格的残差学习和沙漏密集的块学习的新骨干,术语U-HOLGLASS密集网络(U-HDN),这是一个理论上和实验,最大限度地提高IKM的效力。单图像超分辨率的广泛实验表明,该方法实现了优异的现有方法性能。代码可在github.com/yuanfeihuang/ikm获得。
translated by 谷歌翻译
基于卷积神经网络(CNN)的现代单图像超分辨率(SISR)系统实现了花哨的性能,而需要巨大的计算成本。在视觉识别任务中对特征冗余的问题进行了很好的研究,但很少在SISR中进行讨论。基于这样的观察,SISR模型中的许多功能也彼此相似,我们建议使用Shift操作来生成冗余功能(即幽灵功能)。与在类似GPU的设备上耗时的深度卷积相比,Shift操作可以为CNN带来实用的推理加速度。我们分析了SISR操作对SISR任务的好处,并根据Gumbel-SoftMax技巧使Shift取向可学习。此外,基于预训练的模型探索了聚类过程,以识别用于生成内在特征的内在过滤器。幽灵功能将通过沿特定方向移动这些内在功能来得出。最后,完整的输出功能是通过将固有和幽灵特征串联在一起来构建的。在几个基准模型和数据集上进行的广泛实验表明,嵌入了所提出方法的非压缩和轻质SISR模型都可以实现与基准的可比性能,并大大降低了参数,拖台和GPU推荐延迟。例如,我们将参数降低46%,FLOPS掉落46%,而GPU推断潜伏期则减少了$ \ times2 $ EDSR网络的42%,基本上是无损的。
translated by 谷歌翻译
Blind image super-resolution (Blind-SR) aims to recover a high-resolution (HR) image from its corresponding low-resolution (LR) input image with unknown degradations. Most of the existing works design an explicit degradation estimator for each degradation to guide SR. However, it is infeasible to provide concrete labels of multiple degradation combinations (\eg, blur, noise, jpeg compression) to supervise the degradation estimator training. In addition, these special designs for certain degradation, such as blur, impedes the models from being generalized to handle different degradations. To this end, it is necessary to design an implicit degradation estimator that can extract discriminative degradation representation for all degradations without relying on the supervision of degradation ground-truth. In this paper, we propose a Knowledge Distillation based Blind-SR network (KDSR). It consists of a knowledge distillation based implicit degradation estimator network (KD-IDE) and an efficient SR network. To learn the KDSR model, we first train a teacher network: KD-IDE$_{T}$. It takes paired HR and LR patches as inputs and is optimized with the SR network jointly. Then, we further train a student network KD-IDE$_{S}$, which only takes LR images as input and learns to extract the same implicit degradation representation (IDR) as KD-IDE$_{T}$. In addition, to fully use extracted IDR, we design a simple, strong, and efficient IDR based dynamic convolution residual block (IDR-DCRB) to build an SR network. We conduct extensive experiments under classic and real-world degradation settings. The results show that KDSR achieves SOTA performance and can generalize to various degradation processes. The source codes and pre-trained models will be released.
translated by 谷歌翻译