Considering the spectral properties of images, we propose a new self-attention mechanism with highly reduced computational complexity, up to a linear rate. To better preserve edges while promoting similarity within objects, we propose individualized processes over different frequency bands. In particular, we study a case where the process is merely over low-frequency components. By ablation study, we show that low frequency self-attention can achieve very close or better performance relative to full frequency even without retraining the network. Accordingly, we design and embed novel plug-and-play modules to the head of a CNN network that we refer to as FsaNet. The frequency self-attention 1) takes low frequency coefficients as input, 2) can be mathematically equivalent to spatial domain self-attention with linear structures, 3) simplifies token mapping ($1\times1$ convolution) stage and token mixing stage simultaneously. We show that the frequency self-attention requires $87.29\% \sim 90.04\%$ less memory, $96.13\% \sim 98.07\%$ less FLOPs, and $97.56\% \sim 98.18\%$ in run time than the regular self-attention. Compared to other ResNet101-based self-attention networks, FsaNet achieves a new state-of-the-art result ($83.0\%$ mIoU) on Cityscape test dataset and competitive results on ADE20k and VOCaug.
translated by 谷歌翻译
视觉表示学习是解决各种视力问题的关键。依靠开创性的网格结构先验,卷积神经网络(CNN)已成为大多数深视觉模型的事实上的标准架构。例如,经典的语义分割方法通常采用带有编码器编码器体系结构的完全横向卷积网络(FCN)。编码器逐渐减少了空间分辨率,并通过更大的接受场来学习更多抽象的视觉概念。由于上下文建模对于分割至关重要,因此最新的努力一直集中在通过扩张(即极度)卷积或插入注意力模块来增加接受场。但是,基于FCN的体系结构保持不变。在本文中,我们旨在通过将视觉表示学习作为序列到序列预测任务来提供替代观点。具体而言,我们部署纯变压器以将图像编码为一系列贴片,而无需局部卷积和分辨率减少。通过在变压器的每一层中建立的全球环境,可以学习更强大的视觉表示形式,以更好地解决视力任务。特别是,我们的细分模型(称为分割变压器(SETR))在ADE20K上擅长(50.28%MIOU,这是提交当天测试排行榜中的第一个位置),Pascal环境(55.83%MIOU),并在CityScapes上达到竞争成果。此外,我们制定了一个分层局部全球(HLG)变压器的家族,其特征是窗户内的本地关注和跨窗户的全球性专注于层次结构和金字塔架构。广泛的实验表明,我们的方法在各种视觉识别任务(例如,图像分类,对象检测和实例分割和语义分割)上实现了吸引力的性能。
translated by 谷歌翻译
Contextual information is vital in visual understanding problems, such as semantic segmentation and object detection. We propose a Criss-Cross Network (CCNet) for obtaining full-image contextual information in a very effective and efficient way. Concretely, for each pixel, a novel criss-cross attention module harvests the contextual information of all the pixels on its criss-cross path. By taking a further recurrent operation, each pixel can finally capture the full-image dependencies. Besides, a category consistent loss is proposed to enforce the criss-cross attention module to produce more discriminative features. Overall, CCNet is with the following merits: 1) GPU memory friendly. Compared with the non-local block, the proposed recurrent criss-cross attention module requires 11× less GPU memory usage. 2) High computational efficiency. The recurrent criss-cross attention significantly reduces FLOPs by about 85% of the non-local block. 3) The state-of-the-art performance. We conduct extensive experiments on semantic segmentation benchmarks including Cityscapes, ADE20K, human parsing benchmark LIP, instance segmentation benchmark COCO, video segmentation benchmark CamVid. In particular, our CCNet achieves the mIoU scores of 81.9%, 45.76% and 55.47% on the Cityscapes test set, the ADE20K validation set and the LIP validation set respectively, which are the new state-of-the-art results. The source codes are available at https://github.com/speedinghzl/CCNet.
translated by 谷歌翻译
最近的非本地自我关注方法已经证明是有效地捕获用于语义细分的远程依赖性。这些方法通常形成RC * C的相似性图(通过压缩空间尺寸)或rhW * HW(通过压缩通道)来描述沿通道或空间尺寸的特征关系,其中C是通道,H和W的数量输入特征映射的空间尺寸。然而,这种做法倾向于沿着其他尺寸的浓缩特征依赖性,因此引起注意丢失,这可能导致小型/薄类别或大物体内部不一致的分割结果。为了解决这个问题,我们提出了一种重新的方法,即完全注意网络(FLANET),以编码单个相似性图中的空间和频道注意,同时保持高计算效率。具体地,对于每个频道图,我们的枫套可以通过新颖的完全注意模块收获来自所有其他信道地图的特征响应和相关的空间位置。我们的新方法在三个具有挑战性的语义细分数据集中实现了最先进的性能,即在城市景观测试集,ADE20K验证集和Pascal VOC测试集中的83.6%,46.99%和88.5% 。
translated by 谷歌翻译
Vision transformers (ViTs) encoding an image as a sequence of patches bring new paradigms for semantic segmentation.We present an efficient framework of representation separation in local-patch level and global-region level for semantic segmentation with ViTs. It is targeted for the peculiar over-smoothness of ViTs in semantic segmentation, and therefore differs from current popular paradigms of context modeling and most existing related methods reinforcing the advantage of attention. We first deliver the decoupled two-pathway network in which another pathway enhances and passes down local-patch discrepancy complementary to global representations of transformers. We then propose the spatially adaptive separation module to obtain more separate deep representations and the discriminative cross-attention which yields more discriminative region representations through novel auxiliary supervisions. The proposed methods achieve some impressive results: 1) incorporated with large-scale plain ViTs, our methods achieve new state-of-the-art performances on five widely used benchmarks; 2) using masked pre-trained plain ViTs, we achieve 68.9% mIoU on Pascal Context, setting a new record; 3) pyramid ViTs integrated with the decoupled two-pathway network even surpass the well-designed high-resolution ViTs on Cityscapes; 4) the improved representations by our framework have favorable transferability in images with natural corruptions. The codes will be released publicly.
translated by 谷歌翻译
视觉变压器在众多计算机视觉任务上表现出了巨大的成功。然而,由于计算复杂性和记忆足迹是二次的,因此其中心分量(软磁性注意力)禁止视觉变压器扩展到高分辨率图像。尽管在自然语言处理(NLP)任务中引入了线性注意以减轻类似问题,但直接将现有的线性注意力应用于视觉变压器可能不会导致令人满意的结果。我们研究了这个问题,发现与NLP任务相比,计算机视觉任务更多地关注本地信息。基于这一观察结果,我们提出了附近的关注,该关注引入了具有线性复杂性的视觉变压器的局部性偏见。具体而言,对于每个图像补丁,我们根据其相邻贴片测量的2D曼哈顿距离调整了注意力重量。在这种情况下,相邻的补丁比遥远的补丁会受到更大的关注。此外,由于我们的附近注意力要求令牌长度比特征维度大得多,以显示其效率优势,因此我们进一步提出了一个新的附近视觉变压器(VVT)结构,以减少特征维度而不脱离准确性。我们在CIFAR100,ImagEnet1k和ADE20K数据集上进行了广泛的实验,以验证我们方法的有效性。当输入分辨率增加时,与以前的基于变压器和基于卷积的网络相比,GFLOP的增长率较慢。特别是,我们的方法达到了最新的图像分类精度,其参数比以前的方法少50%。
translated by 谷歌翻译
Semantic segmentation usually benefits from global contexts, fine localisation information, multi-scale features, etc. To advance Transformer-based segmenters with these aspects, we present a simple yet powerful semantic segmentation architecture, termed as IncepFormer. IncepFormer has two critical contributions as following. First, it introduces a novel pyramid structured Transformer encoder which harvests global context and fine localisation features simultaneously. These features are concatenated and fed into a convolution layer for final per-pixel prediction. Second, IncepFormer integrates an Inception-like architecture with depth-wise convolutions, and a light-weight feed-forward module in each self-attention layer, efficiently obtaining rich local multi-scale object features. Extensive experiments on five benchmarks show that our IncepFormer is superior to state-of-the-art methods in both accuracy and speed, e.g., 1) our IncepFormer-S achieves 47.7% mIoU on ADE20K which outperforms the existing best method by 1% while only costs half parameters and fewer FLOPs. 2) Our IncepFormer-B finally achieves 82.0% mIoU on Cityscapes dataset with 39.6M parameters. Code is available:github.com/shendu0321/IncepFormer.
translated by 谷歌翻译
在本文中,我们专注于探索有效的方法,以更快,准确和域的不可知性语义分割。受到相邻视频帧之间运动对齐的光流的启发,我们提出了一个流对齐模块(FAM),以了解相邻级别的特征映射之间的\ textit {语义流},并将高级特征广播到高分辨率特征有效地,有效地有效。 。此外,将我们的FAM与共同特征的金字塔结构集成在一起,甚至在轻量重量骨干网络(例如Resnet-18和DFNET)上也表现出优于其他实时方法的性能。然后,为了进一步加快推理过程,我们还提出了一个新型的封闭式双流对齐模块,以直接对齐高分辨率特征图和低分辨率特征图,在该图中我们将改进版本网络称为SFNET-LITE。广泛的实验是在几个具有挑战性的数据集上进行的,结果显示了SFNET和SFNET-LITE的有效性。特别是,建议的SFNET-LITE系列在使用RESNET-18主链和78.8 MIOU以120 fps运行的情况下,使用RTX-3090上的STDC主链在120 fps运行时,在60 fps运行时达到80.1 miou。此外,我们将四个具有挑战性的驾驶数据集(即CityScapes,Mapillary,IDD和BDD)统一到一个大数据集中,我们将其命名为Unified Drive细分(UDS)数据集。它包含不同的域和样式信息。我们基准了UDS上的几项代表性作品。 SFNET和SFNET-LITE仍然可以在UDS上取得最佳的速度和准确性权衡,这在如此新的挑战性环境中是强大的基准。所有代码和模型均可在https://github.com/lxtgh/sfsegnets上公开获得。
translated by 谷歌翻译
人类自然有效地在复杂的场景中找到突出区域。通过这种观察的动机,引入了计算机视觉中的注意力机制,目的是模仿人类视觉系统的这一方面。这种注意机制可以基于输入图像的特征被视为动态权重调整过程。注意机制在许多视觉任务中取得了巨大的成功,包括图像分类,对象检测,语义分割,视频理解,图像生成,3D视觉,多模态任务和自我监督的学习。在本调查中,我们对计算机愿景中的各种关注机制进行了全面的审查,并根据渠道注意,空间关注,暂时关注和分支注意力进行分类。相关的存储库https://github.com/menghaoguo/awesome-vision-tions致力于收集相关的工作。我们还建议了未来的注意机制研究方向。
translated by 谷歌翻译
多层erceptron(MLP),作为出现的第一个神经网络结构,是一个大的击中。但是由硬件计算能力和数据集的大小限制,它一旦沉没了数十年。在此期间,我们目睹了从手动特征提取到带有局部接收领域的CNN的范式转变,以及基于自我关注机制的全球接收领域的变换。今年(2021年),随着MLP混合器的推出,MLP已重新进入敏捷,并吸引了计算机视觉界的广泛研究。与传统的MLP进行比较,它变得更深,但改变了完全扁平化以补丁平整的输入。鉴于其高性能和较少的需求对视觉特定的感应偏见,但社区无法帮助奇迹,将MLP,最简单的结构与全球接受领域,但没有关注,成为一个新的电脑视觉范式吗?为了回答这个问题,本调查旨在全面概述视觉深层MLP模型的最新发展。具体而言,我们从微妙的子模块设计到全局网络结构,我们审查了这些视觉深度MLP。我们比较了不同网络设计的接收领域,计算复杂性和其他特性,以便清楚地了解MLP的开发路径。调查表明,MLPS的分辨率灵敏度和计算密度仍未得到解决,纯MLP逐渐发展朝向CNN样。我们建议,目前的数据量和计算能力尚未准备好接受纯的MLP,并且人工视觉指导仍然很重要。最后,我们提供了开放的研究方向和可能的未来作品的分析。我们希望这项努力能够点燃社区的进一步兴趣,并鼓励目前为神经网络进行更好的视觉量身定制设计。
translated by 谷歌翻译
语义分割是自主车辆了解周围场景的关键技术。当代模型的吸引力表现通常以牺牲重计算和冗长的推理时间为代价,这对于自行车来说是无法忍受的。在低分辨率图像上使用轻量级架构(编码器 - 解码器或双路)或推理,最近的方法实现了非常快的场景解析,即使在单个1080TI GPU上以100多件FPS运行。然而,这些实时方法与基于扩张骨架的模型之间的性能仍有显着差距。为了解决这个问题,我们提出了一家专门为实时语义细分设计的高效底座。所提出的深层双分辨率网络(DDRNET)由两个深部分支组成,之间进行多个双边融合。此外,我们设计了一个名为Deep聚合金字塔池(DAPPM)的新上下文信息提取器,以基于低分辨率特征映射放大有效的接收字段和熔丝多尺度上下文。我们的方法在城市景观和Camvid数据集上的准确性和速度之间实现了新的最先进的权衡。特别是,在单一的2080Ti GPU上,DDRNET-23-Slim在Camvid测试组上的Citycapes试验组102 FPS上的102 FPS,74.7%Miou。通过广泛使用的测试增强,我们的方法优于最先进的模型,需要计算得多。 CODES和培训的型号在线提供。
translated by 谷歌翻译
现代的高性能语义分割方法采用沉重的主链和扩张的卷积来提取相关特征。尽管使用上下文和语义信息提取功能对于分割任务至关重要,但它为实时应用程序带来了内存足迹和高计算成本。本文提出了一种新模型,以实现实时道路场景语义细分的准确性/速度之间的权衡。具体来说,我们提出了一个名为“比例吸引的条带引导特征金字塔网络”(s \ textsuperscript {2} -fpn)的轻巧模型。我们的网络由三个主要模块组成:注意金字塔融合(APF)模块,比例吸引条带注意模块(SSAM)和全局特征Upsample(GFU)模块。 APF采用了注意力机制来学习判别性多尺度特征,并有助于缩小不同级别之间的语义差距。 APF使用量表感知的关注来用垂直剥离操作编码全局上下文,并建模长期依赖性,这有助于将像素与类似的语义标签相关联。此外,APF还采用频道重新加权块(CRB)来强调频道功能。最后,S \ TextSuperScript {2} -fpn的解码器然后采用GFU,该GFU用于融合APF和编码器的功能。已经对两个具有挑战性的语义分割基准进行了广泛的实验,这表明我们的方法通过不同的模型设置实现了更好的准确性/速度权衡。提出的模型已在CityScapes Dataset上实现了76.2 \%miou/87.3fps,77.4 \%miou/67fps和77.8 \%miou/30.5fps,以及69.6 \%miou,71.0 miou,71.0 \%miou,和74.2 \%\%\%\%\%\%。 miou在Camvid数据集上。这项工作的代码将在\ url {https://github.com/mohamedac29/s2-fpn提供。
translated by 谷歌翻译
Semantic segmentation is a classic computer vision problem dedicated to labeling each pixel with its corresponding category. As a basic task for advanced tasks such as industrial quality inspection, remote sensing information extraction, medical diagnostic aid, and autonomous driving, semantic segmentation has been developed for a long time in combination with deep learning, and a lot of works have been accumulated. However, neither the classic FCN-based works nor the popular Transformer-based works have attained fine-grained localization of pixel labels, which remains the main challenge in this field. Recently, with the popularity of autonomous driving, the segmentation of road scenes has received increasing attention. Based on the cross-task consistency theory, we incorporate edge priors into semantic segmentation tasks to obtain better results. The main contribution is that we provide a model-agnostic method that improves the accuracy of semantic segmentation models with zero extra inference runtime overhead, verified on the datasets of road and non-road scenes. From our experimental results, our method can effectively improve semantic segmentation accuracy.
translated by 谷歌翻译
大型预训练的变压器是现代语义分割基准的顶部,但具有高计算成本和冗长的培训。为了提高这种约束,我们从综合知识蒸馏的角度来研究有效的语义分割,并考虑弥合多源知识提取和特定于变压器特定的斑块嵌入之间的差距。我们提出了基于变压器的知识蒸馏(TransKD)框架,该框架通过蒸馏出大型教师变压器的特征地图和补丁嵌入来学习紧凑的学生变形金刚,绕过长期的预训练过程并将FLOPS降低> 85.0%。具体而言,我们提出了两个基本和两个优化模块:(1)交叉选择性融合(CSF)可以通过通道注意和层次变压器内的特征图蒸馏之间的知识转移; (2)嵌入对齐(PEA)在斑块过程中执行尺寸转换,以促进贴片嵌入蒸馏; (3)全局本地上下文混合器(GL-MIXER)提取了代表性嵌入的全局和局部信息; (4)嵌入助手(EA)是一种嵌入方法,可以无缝地桥接老师和学生模型,并具有老师的渠道数量。关于CityScapes,ACDC和NYUV2数据集的实验表明,TransKD的表现优于最先进的蒸馏框架,并竞争了耗时的预训练方法。代码可在https://github.com/ruipingl/transkd上找到。
translated by 谷歌翻译
Transformers have proved to be very effective for visual recognition tasks. In particular, vision transformers construct compressed global representations through self-attention and learnable class tokens. Multi-resolution transformers have shown recent successes in semantic segmentation but can only capture local interactions in high-resolution feature maps. This paper extends the notion of global tokens to build GLobal Attention Multi-resolution (GLAM) transformers. GLAM is a generic module that can be integrated into most existing transformer backbones. GLAM includes learnable global tokens, which unlike previous methods can model interactions between all image regions, and extracts powerful representations during training. Extensive experiments show that GLAM-Swin or GLAM-Swin-UNet exhibit substantially better performances than their vanilla counterparts on ADE20K and Cityscapes. Moreover, GLAM can be used to segment large 3D medical images, and GLAM-nnFormer achieves new state-of-the-art performance on the BCV dataset.
translated by 谷歌翻译
利用多尺度功能在解决语义细分问题方面表现出了巨大的潜力。聚集通常是用总和或串联(Concat)进行的,然后是卷积(Conv)层。但是,它将高级上下文完全通过了以下层次结构,而无需考虑它们的相互关系。在这项工作中,我们旨在启用低级功能,以通过跨尺度像素到区域关系操作从相邻的高级特征图中汇总互补上下文。我们利用跨尺度上下文的传播,即使高分辨率的低级特征也可以使远程依赖关系也可以捕获。为此,我们采用有效的功能金字塔网络来获得多尺度功能。我们提出了一个关系语义提取器(RSE)和关系语义传播器(RSP),分别用于上下文提取和传播。然后,我们将几个RSP堆叠到RSP头中,以实现上下文的渐进自上而下分布。两个具有挑战性的数据集和可可的实验结果表明,RSP头在语义细分和泛型分割方面都具有高效率的竞争性。在语义分割任务中,它的表现优于DeepLabv3 [1],而在语义分割任务中少75%(多重添加)。
translated by 谷歌翻译
夜间场景解析(NTSP)对于许多视觉应用是必不可少的,尤其是对于自动驾驶。大多数现有方法都是为了解析白天的现有方法。他们依靠在照明下建模基于像素强度的空间上下文线索。因此,这些方法在夜间场景中表现不佳,因为这种空间上下文提示被埋葬在夜间场景中的过度/暴露区域中。在本文中,我们首先进行了基于图像频率的统计实验来解释白天和夜间场景差异。我们发现,在白天和夜间场景之间,图像频率分布有很大差异,并且了解此类频率分布对于NTSP问题至关重要。基于此,我们建议利用图像频率分布来解析夜间场景。首先,我们提出了一个可学习的频率编码器(LFE),以模拟不同频率系数之间的关系,以动态测量所有频率组件。其次,我们提出了一个空间频率融合模块(SFF),该模块融合了空间和频率信息,以指导空间上下文特征的提取。广泛的实验表明,我们的方法对夜总会,夜城+和BDD100K晚数据集的最先进方法表现出色。此外,我们证明我们的方法可以应用于现有的白天场景解析方法,并在夜间场景中提高其性能。
translated by 谷歌翻译
Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoderdecoder architecture. The encoder progressively reduces the spatial resolution and learns more abstract/semantic visual concepts with larger receptive fields. Since context modeling is critical for segmentation, the latest efforts have been focused on increasing the receptive field, through either dilated/atrous convolutions or inserting attention modules. However, the encoder-decoder based FCN architecture remains unchanged. In this paper, we aim to provide an alternative perspective by treating semantic segmentation as a sequence-to-sequence prediction task. Specifically, we deploy a pure transformer (i.e., without convolution and resolution reduction) to encode an image as a sequence of patches. With the global context modeled in every layer of the transformer, this encoder can be combined with a simple decoder to provide a powerful segmentation model, termed SEgmentation TRansformer (SETR). Extensive experiments show that SETR achieves new state of the art on ADE20K (50.28% mIoU), Pascal Context (55.83% mIoU) and competitive results on Cityscapes. Particularly, we achieve the first position in the highly competitive ADE20K test server leaderboard on the day of submission.
translated by 谷歌翻译
In this paper, we address the scene segmentation task by capturing rich contextual dependencies based on the self-attention mechanism. Unlike previous works that capture contexts by multi-scale feature fusion, we propose a Dual Attention Network (DANet) to adaptively integrate local features with their global dependencies. Specifically, we append two types of attention modules on top of dilated FCN, which model the semantic interdependencies in spatial and channel dimensions respectively. The position attention module selectively aggregates the feature at each position by a weighted sum of the features at all positions. Similar features would be related to each other regardless of their distances. Meanwhile, the channel attention module selectively emphasizes interdependent channel maps by integrating associated features among all channel maps. We sum the outputs of the two attention modules to further improve feature representation which contributes to more precise segmentation results. We achieve new state-of-theart segmentation performance on three challenging scene segmentation datasets, i.e., Cityscapes, PASCAL Context and COCO Stuff dataset. In particular, a Mean IoU score of 81.5% on Cityscapes test set is achieved without using coarse data. 1 .
translated by 谷歌翻译
多尺度表示对于语义细分至关重要。社区目睹了利用多尺度上下文信息的语义分割卷积神经网络(CNN)的蓬勃发展。通过视觉变压器(VIV)的动机是强大的图像分类,最近提出了一些语义分割VITS,其中大多数是令人印象深刻的结果,但以计算经济为代价。在本文中,我们通过窗口注意机制成功地将多尺度表示引入语义分割vit,并进一步提高了性能和效率。为此,我们介绍了大型窗口关注,允许本地窗口在略微计算开销时仅查询大面积的上下文窗口。通过调节上下文区域与查询区域的比率,我们可以在多个尺度上捕获大量窗口注意。此外,采用空间金字塔汇集的框架与大窗口关注合作,这提出了一种名为大型窗口注意空​​间金字塔池(LawinAspp)的新型解码器,用于语义细分vit。我们所产生的Vit,草坪变压器由一个高效的定理视觉变压器(HVT)作为编码器和作为解码器的草坪Appp。实证结果表明,与现有方法相比,草坪变压器提供了提高的效率。草坪变压器进一步为城市景观(84.4 \%Miou),ADE20K(56.2 \%Miou)和Coco-incumate集进行了新的最先进的性能。代码将在https://github.com/yan-hao-tian/lawin发布。
translated by 谷歌翻译