传统的域自适应语义细分解决了在有限或没有其他监督下,将模型调整为新的目标域的任务。在解决输入域间隙的同时,标准域的适应设置假设输出空间没有域的变化。在语义预测任务中,通常根据不同的语义分类法标记不同的数据集。在许多现实世界中,目标域任务需要与源域施加的分类法不同。因此,我们介绍了更通用的自适应跨域语义细分(TAC)问题,从而使两个域之间的分类学不一致。我们进一步提出了一种共同解决图像级和标签级域适应的方法。在标签级别上,我们采用双边混合采样策略来增强目标域,并采用重新标记方法来统一和对齐标签空间。我们通过提出一种不确定性构造的对比度学习方法来解决图像级域间隙,从而导致更多的域不变和类别的歧义特征。我们在不同的TACS设置下广泛评估了框架的有效性:开放分类法,粗到精细的分类学和隐式重叠的分类学。我们的方法的表现超过了先前的最先进的利润,同时能够适应目标分类法。我们的实施可在https://github.com/ethruigong/tada上公开获得。
translated by 谷歌翻译
Unsupervised sim-to-real domain adaptation (UDA) for semantic segmentation aims to improve the real-world test performance of a model trained on simulated data. It can save the cost of manually labeling data in real-world applications such as robot vision and autonomous driving. Traditional UDA often assumes that there are abundant unlabeled real-world data samples available during training for the adaptation. However, such an assumption does not always hold in practice owing to the collection difficulty and the scarcity of the data. Thus, we aim to relieve this need on a large number of real data, and explore the one-shot unsupervised sim-to-real domain adaptation (OSUDA) and generalization (OSDG) problem, where only one real-world data sample is available. To remedy the limited real data knowledge, we first construct the pseudo-target domain by stylizing the simulated data with the one-shot real data. To mitigate the sim-to-real domain gap on both the style and spatial structure level and facilitate the sim-to-real adaptation, we further propose to use class-aware cross-domain transformers with an intermediate domain randomization strategy to extract the domain-invariant knowledge, from both the simulated and pseudo-target data. We demonstrate the effectiveness of our approach for OSUDA and OSDG on different benchmarks, outperforming the state-of-the-art methods by a large margin, 10.87, 9.59, 13.05 and 15.91 mIoU on GTA, SYNTHIA$\rightarrow$Cityscapes, Foggy Cityscapes, respectively.
translated by 谷歌翻译
虽然监督语义分割存在重大进展,但由于领域偏差,将分段模型部署到解除域来仍然具有挑战性。域适应可以通过将知识从标记的源域传输到未标记的目标域来帮助。以前的方法通常尝试执行对全局特征的适应,然而,通常忽略要计入特征空间中的每个像素的本地语义附属机构,导致较少的可辨性。为解决这个问题,我们提出了一种用于细粒度阶级对齐的新型语义原型对比学习框架。具体地,语义原型提供了用于每个像素鉴别的表示学习的监控信号,并且需要在特征空间中的源极和目标域的每个像素来反映相应的语义原型的内容。通过这种方式,我们的框架能够明确地制作较近的类别的像素表示,并且进一步越来越多地分开,以改善分割模型的鲁棒性以及减轻域移位问题。与最先进的方法相比,我们的方法易于实施并达到优异的结果,如众多实验所展示的那样。代码在[此HTTPS URL](https://github.com/binhuixie/spcl)上公开可用。
translated by 谷歌翻译
In unsupervised domain adaptation (UDA), a model trained on source data (e.g. synthetic) is adapted to target data (e.g. real-world) without access to target annotation. Most previous UDA methods struggle with classes that have a similar visual appearance on the target domain as no ground truth is available to learn the slight appearance differences. To address this problem, we propose a Masked Image Consistency (MIC) module to enhance UDA by learning spatial context relations of the target domain as additional clues for robust visual recognition. MIC enforces the consistency between predictions of masked target images, where random patches are withheld, and pseudo-labels that are generated based on the complete image by an exponential moving average teacher. To minimize the consistency loss, the network has to learn to infer the predictions of the masked regions from their context. Due to its simple and universal concept, MIC can be integrated into various UDA methods across different visual recognition tasks such as image classification, semantic segmentation, and object detection. MIC significantly improves the state-of-the-art performance across the different recognition tasks for synthetic-to-real, day-to-nighttime, and clear-to-adverse-weather UDA. For instance, MIC achieves an unprecedented UDA performance of 75.9 mIoU and 92.8% on GTA-to-Cityscapes and VisDA-2017, respectively, which corresponds to an improvement of +2.1 and +3.0 percent points over the previous state of the art. The implementation is available at https://github.com/lhoyer/MIC.
translated by 谷歌翻译
在这项工作中,我们提出了Cluda,这是一种简单而又新颖的方法,用于通过将对比损失纳入学生教师学习范式中,以进行语义分割,以进行语义分割,以利用伪标记,以通过伪标记产生的伪标记。教师网络。更具体地说,我们从编码器中提取多级融合功能图,并通过图像的源目标混合使用不同类别和不同域的对比度损失。我们始终提高各种特征编码器体系结构和语义分割中不同域适应数据集的性能。此外,我们引入了一种学识渊博的对比损失,以改善UDA最先进的多分辨率训练方法。我们在gta $ \ rightarrow $ cityScapes(74.4 miou,+0.6)和Synthia $ \ rightarrow $ cityScapes(67.2 miou,+1.4)数据集上产生最先进的结果。 Cluda有效地证明了UDA中的对比度学习是一种通用方法,可以轻松地将其集成到任何现有的UDA中以进行语义分割任务。有关实施的详细信息,请参考补充材料。
translated by 谷歌翻译
无监督的域适应性(UDA)旨在使在标记的源域上训练的模型适应未标记的目标域。在本文中,我们提出了典型的对比度适应(PROCA),这是一种无监督域自适应语义分割的简单有效的对比度学习方法。以前的域适应方法仅考虑跨各个域的阶级内表示分布的对齐,而阶层间结构关系的探索不足,从而导致目标域上的对齐表示可能不像在源上歧视的那样容易歧视。域了。取而代之的是,ProCA将类间信息纳入班级原型,并采用以班级为中心的分布对齐进行适应。通过将同一类原型与阳性和其他类原型视为实现以集体为中心的分配对齐方式的负面原型,Proca在经典领域适应任务上实现了最先进的性能,{\ em i.e. text {and} synthia $ \ to $ cityScapes}。代码可在\ href {https://github.com/jiangzhengkai/proca} {proca}获得代码
translated by 谷歌翻译
由于获取对语义分割的实际图像的像素明智的注释是一个昂贵的过程,模型可以通过更多可访问的合成数据训练,并且适应真实图像而不需要其注释。在无监督的域适应(UDA)中研究了该过程。尽管大量方法提出了新的适应策略,但它们主要基于过时的网络架构。由于尚未系统地研究了网络架构的影响,我们首先为UDA进行基准标记不同的网络架构,然后提出基于基准结果的新型UDA方法Daformer。 DAFormer网络由变压器编码器和多级上下文感知功能融合解码器组成。它通过三种简单但重要的培训策略使稳定培训并避免将DAFFormer过度装箱到源域:虽然通过减轻自我训练的确认偏差来提高源域上的罕见类别提高了伪标签的质量常见的类,Thing-Class Imagenet特征距离和学习率预热促进了从想象成预介绍的功能转移。 Daformer显着提高了最先进的性能,通过10.8 Miou for GTA-> Citycapes和5.4 Miou for Synthia-> Citycapes,并使得甚至是学习甚至困难的课程,如火车,公共汽车和卡车。该实现可在https://github.com/lhoyer/daformer中获得。
translated by 谷歌翻译
受益于从特定情况(源)收集的相当大的像素级注释,训练有素的语义分段模型表现得非常好,但由于大域移位而导致的新情况(目标)失败。为了缓解域间隙,先前的跨域语义分段方法始终在域对齐期间始终假设源数据和目标数据的共存。但是,在实际方案中访问源数据可能会引发隐私问题并违反知识产权。为了解决这个问题,我们专注于一个有趣和具有挑战性的跨域语义分割任务,其中仅向目标域提供训练源模型。具体地,我们提出了一种称为ATP的统一框架,其包括三种方案,即特征对准,双向教学和信息传播。首先,我们设计了课程熵最小化目标,以通过提供的源模型隐式对准目标功能与看不见的源特征。其次,除了vanilla自我训练中的正伪标签外,我们是第一个向该领域引入负伪标签的,并开发双向自我训练策略,以增强目标域中的表示学习。最后,采用信息传播方案来通过伪半监督学习进一步降低目标域内的域内差异。综合与跨城市驾驶数据集的广泛结果验证\ TextBF {ATP}产生最先进的性能,即使是需要访问源数据的方法。
translated by 谷歌翻译
无监督的域适应性(UDA)旨在使标记的源域的模型适应未标记的目标域。现有的基于UDA的语义细分方法始终降低像素级别,功能级别和输出级别的域移动。但是,几乎所有这些都在很大程度上忽略了上下文依赖性,该依赖性通常在不同的领域共享,从而导致较不怀疑的绩效。在本文中,我们提出了一个新颖的环境感知混音(camix)框架自适应语义分割的框架,该框架以完全端到端的可训练方式利用了上下文依赖性的这一重要线索作为显式的先验知识,以增强对适应性的适应性目标域。首先,我们通过利用积累的空间分布和先前的上下文关系来提出上下文掩盖的生成策略。生成的上下文掩码在这项工作中至关重要,并将指导三个不同级别的上下文感知域混合。此外,提供了背景知识,我们引入了重要的一致性损失,以惩罚混合学生预测与混合教师预测之间的不一致,从而减轻了适应性的负面转移,例如早期绩效降级。广泛的实验和分析证明了我们方法对广泛使用的UDA基准的最新方法的有效性。
translated by 谷歌翻译
深度学习极大地提高了语义细分的性能,但是,它的成功依赖于大量注释的培训数据的可用性。因此,许多努力致力于域自适应语义分割,重点是将语义知识从标记的源域转移到未标记的目标域。现有的自我训练方法通常需要多轮训练,而基于对抗训练的另一个流行框架已知对超参数敏感。在本文中,我们提出了一个易于训练的框架,该框架学习了域自适应语义分割的域不变原型。特别是,我们表明域的适应性与很少的学习共享一个共同的角色,因为两者都旨在识别一些从大量可见数据中学到的知识的看不见的数据。因此,我们提出了一个统一的框架,用于域适应和很少的学习。核心思想是使用从几个镜头注释的目标图像中提取的类原型来对源图像和目标图像的像素进行分类。我们的方法仅涉及一个阶段训练,不需要对大规模的未经通知的目标图像进行培训。此外,我们的方法可以扩展到域适应性和几乎没有射击学习的变体。关于适应GTA5到CITYSCAPES和合成景观的实验表明,我们的方法实现了对最先进的竞争性能。
translated by 谷歌翻译
语义分割在广泛的计算机视觉应用中起着基本作用,提供了全球对图像​​的理解的关键信息。然而,最先进的模型依赖于大量的注释样本,其比在诸如图像分类的任务中获得更昂贵的昂贵的样本。由于未标记的数据替代地获得更便宜,因此无监督的域适应达到了语义分割社区的广泛成功并不令人惊讶。本调查致力于总结这一令人难以置信的快速增长的领域的五年,这包含了语义细分本身的重要性,以及将分段模型适应新环境的关键需求。我们提出了最重要的语义分割方法;我们对语义分割的域适应技术提供了全面的调查;我们揭示了多域学习,域泛化,测试时间适应或无源域适应等较新的趋势;我们通过描述在语义细分研究中最广泛使用的数据集和基准测试来结束本调查。我们希望本调查将在学术界和工业中提供具有全面参考指导的研究人员,并有助于他们培养现场的新研究方向。
translated by 谷歌翻译
在大量标记培训数据的监督下,视频语义细分取得了巨大进展。但是,域自适应视频分割,可以通过从标记的源域对未标记的目标域进行调整来减轻数据标记约束,这很大程度上被忽略了。我们设计了时间伪监督(TPS),这是一种简单有效的方法,探讨了从未标记的目标视频学习有效表示的一致性培训的想法。与在空间空间中建立一致性的传统一致性训练不同,我们通过在增强视频框架之间执行模型一致性来探索时空空间中的一致性训练,这有助于从更多样化的目标数据中学习。具体来说,我们设计了跨框架伪标签,以从以前的视频帧中提供伪监督,同时从增强的当前视频帧中学习。跨框架伪标签鼓励网络产生高确定性预测,从而有效地通过跨框架增强来促进一致性训练。对多个公共数据集进行的广泛实验表明,与最先进的ART相比,TPS更容易实现,更稳定,并且可以实现卓越的视频细分精度。
translated by 谷歌翻译
在无监督的域自适应(UDA)语义分割中,基于蒸馏的方法目前在性能上占主导地位。但是,蒸馏技术需要使多阶段的过程和许多培训技巧复杂化。在本文中,我们提出了一种简单而有效的方法,可以实现高级蒸馏方法的竞争性能。我们的核心思想是从边界和功能的观点充分探索目标域信息。首先,我们提出了一种新颖的混合策略,以产生具有地面标签的高质量目标域边界。与以前的作品中的源域边界不同,我们选择了高信心目标域区域,然后将其粘贴到源域图像中。这样的策略可以使用正确的标签在目标域(目标域对象区域的边缘)中生成对象边界。因此,可以通过学习混合样品来有效地捕获目标域的边界信息。其次,我们设计了多层对比损失,以改善目标域数据的表示,包括像素级和原型级对比度学习。通过结合两种建议的方法,可以提取更多的判别特征,并且可以更好地解决目标域的硬对象边界。对两个常用基准测试的实验结果(\ textit {i.e。},gta5 $ \ rightarrow $ cityScapes and synthia $ \ rightarrow $ cityScapes)表明,我们的方法在复杂的蒸馏方法上取得了竞争性能。值得注意的是,对于Synthia $ \ rightarrow $ CityScapes方案,我们的方法以$ 57.8 \%$ MIOU和$ 64.6 \%$ MIOU的16堂课和16堂课实现了最先进的性能。代码可在https://github.com/ljjcoder/ehtdi上找到。
translated by 谷歌翻译
近年来,对语义分割的无监督域适应性(UDA)进行了充分研究。但是,大多数现有的作品在很大程度上忽略了不同领域的本地区域一致性,并且对室外环境的变化的鲁棒性较低。在本文中,我们提出了一种新颖且完全端到端的可训练方法,称为域自适应语义分割的区域对比度一致性(RCCR)。我们的核心思想是从不同图像的相同位置提取的相似区域特征,即原始图像和增强图像,以更加接近,同时将两个图像的不同位置的特征推到要分开的不同位置。我们通过两种抽样策略提出了一个区域对比度损失,以实现有效的区域一致性。此外,我们呈现动力投影头,其中教师投射头是学生的指数移动平均值。最后,内存库机制旨在在不同的环境下学习更健壮和稳定的区域特征。对两个常见的UDA基准测试的广泛实验,即GTAV到CityScapes和CityScapes的合成,这表明我们的方法表现优于最先进的方法。
translated by 谷歌翻译
The network trained for domain adaptation is prone to bias toward the easy-to-transfer classes. Since the ground truth label on the target domain is unavailable during training, the bias problem leads to skewed predictions, forgetting to predict hard-to-transfer classes. To address this problem, we propose Cross-domain Moving Object Mixing (CMOM) that cuts several objects, including hard-to-transfer classes, in the source domain video clip and pastes them into the target domain video clip. Unlike image-level domain adaptation, the temporal context should be maintained to mix moving objects in two different videos. Therefore, we design CMOM to mix with consecutive video frames, so that unrealistic movements are not occurring. We additionally propose Feature Alignment with Temporal Context (FATC) to enhance target domain feature discriminability. FATC exploits the robust source domain features, which are trained with ground truth labels, to learn discriminative target domain features in an unsupervised manner by filtering unreliable predictions with temporal consensus. We demonstrate the effectiveness of the proposed approaches through extensive experiments. In particular, our model reaches mIoU of 53.81% on VIPER to Cityscapes-Seq benchmark and mIoU of 56.31% on SYNTHIA-Seq to Cityscapes-Seq benchmark, surpassing the state-of-the-art methods by large margins.
translated by 谷歌翻译
自我训练具有极大的促进域自适应语义分割,它迭代地在目标域上生成伪标签并删除网络。然而,由于现实分割数据集是高度不平衡的,因此目标伪标签通常偏置到多数类并且基本上嘈杂,导致出错和次优模型。为了解决这个问题,我们提出了一个基于区域的主动学习方法,用于在域移位下进行语义分割,旨在自动查询要标记的图像区域的小分区,同时最大化分割性能。我们的算法,通过区域杂质和预测不确定性(AL-RIPU)的主动学习,介绍了一种新的采集策略,其特征在于图像区域的空间邻接以及预测置信度。我们表明,所提出的基于地区的选择策略比基于图像或基于点的对应物更有效地使用有限预算。同时,我们在源图像上强制在像素和其最近邻居之间的局部预测一致性。此外,我们制定了负面学习损失,以提高目标领域的鉴别表现。广泛的实验表明,我们的方法只需要极少的注释几乎达到监督性能,并且大大优于最先进的方法。
translated by 谷歌翻译
Unsupervised source-free domain adaptation methods aim to train a model to be used in the target domain utilizing the pretrained source-domain model and unlabeled target-domain data, where the source data may not be accessible due to intellectual property or privacy issues. These methods frequently utilize self-training with pseudo-labeling thresholded by prediction confidence. In a source-free scenario, only supervision comes from target data, and thresholding limits the contribution of the self-training. In this study, we utilize self-training with a mean-teacher approach. The student network is trained with all predictions of the teacher network. Instead of thresholding the predictions, the gradients calculated from the pseudo-labels are weighted based on the reliability of the teacher's predictions. We propose a novel method that uses proxy-based metric learning to estimate reliability. We train a metric network on the encoder features of the teacher network. Since the teacher is updated with the moving average, the encoder feature space is slowly changing. Therefore, the metric network can be updated in training time, which enables end-to-end training. We also propose a metric-based online ClassMix method to augment the input of the student network where the patches to be mixed are decided based on the metric reliability. We evaluated our method in synthetic-to-real and cross-city scenarios. The benchmarks show that our method significantly outperforms the existing state-of-the-art methods.
translated by 谷歌翻译
Domain adaptation aims to bridge the domain shifts between the source and the target domain. These shifts may span different dimensions such as fog, rainfall, etc. However, recent methods typically do not consider explicit prior knowledge about the domain shifts on a specific dimension, thus leading to less desired adaptation performance. In this paper, we study a practical setting called Specific Domain Adaptation (SDA) that aligns the source and target domains in a demanded-specific dimension. Within this setting, we observe the intra-domain gap induced by different domainness (i.e., numerical magnitudes of domain shifts in this dimension) is crucial when adapting to a specific domain. To address the problem, we propose a novel Self-Adversarial Disentangling (SAD) framework. In particular, given a specific dimension, we first enrich the source domain by introducing a domainness creator with providing additional supervisory signals. Guided by the created domainness, we design a self-adversarial regularizer and two loss functions to jointly disentangle the latent representations into domainness-specific and domainness-invariant features, thus mitigating the intra-domain gap. Our method can be easily taken as a plug-and-play framework and does not introduce any extra costs in the inference time. We achieve consistent improvements over state-of-the-art methods in both object detection and semantic segmentation.
translated by 谷歌翻译
了解驾驶场景中的雾图像序列对于自主驾驶至关重要,但是由于难以收集和注释不利天气的现实世界图像,这仍然是一项艰巨的任务。最近,自我训练策略被认为是无监督域适应的强大解决方案,通过生成目标伪标签并重新训练模型,它迭代地将模型从源域转化为目标域。但是,选择自信的伪标签不可避免地会遭受稀疏与准确性之间的冲突,这两者都会导致次优模型。为了解决这个问题,我们利用了驾驶场景的雾图图像序列的特征,以使自信的伪标签致密。具体而言,基于顺序图像数据的局部空间相似性和相邻时间对应的两个发现,我们提出了一种新型的目标域驱动的伪标签扩散(TDO-DIF)方案。它采用超像素和光学流来识别空间相似性和时间对应关系,然后扩散自信但稀疏的伪像标签,或者是由流量链接的超像素或时间对应对。此外,为了确保扩散像素的特征相似性,我们在模型重新训练阶段引入了局部空间相似性损失和时间对比度损失。实验结果表明,我们的TDO-DIF方案有助于自适应模型在两个公共可用的天然雾化数据集(超过雾气的Zurich and Forggy驾驶)上实现51.92%和53.84%的平均跨工会(MIOU),这超过了最态度ART无监督的域自适应语义分割方法。可以在https://github.com/velor2012/tdo-dif上找到模型和数据。
translated by 谷歌翻译
Recent deep networks achieved state of the art performance on a variety of semantic segmentation tasks. Despite such progress, these models often face challenges in real world "wild tasks" where large difference between labeled training/source data and unseen test/target data exists. In particular, such difference is often referred to as "domain gap", and could cause significantly decreased performance which cannot be easily remedied by further increasing the representation power. Unsupervised domain adaptation (UDA) seeks to overcome such problem without target domain labels. In this paper, we propose a novel UDA framework based on an iterative self-training (ST) procedure, where the problem is formulated as latent variable loss minimization, and can be solved by alternatively generating pseudo labels on target data and re-training the model with these labels. On top of ST, we also propose a novel classbalanced self-training (CBST) framework to avoid the gradual dominance of large classes on pseudo-label generation, and introduce spatial priors to refine generated labels. Comprehensive experiments show that the proposed methods achieve state of the art semantic segmentation performance under multiple major UDA settings.⋆ indicates equal contribution.
translated by 谷歌翻译