图形结构化数据通常在自然界中具有动态字符,例如,在许多现实世界中,链接和节点的添加。近年来见证了对这种图形数据进行建模的动态图神经网络所支付的越来越多的注意力,几乎所有现有方法都假设,当建立新的链接时,应通过学习时间动态来传播邻居节点的嵌入。新的信息。但是,这种方法遭受了这样的限制,如果新连接引入的节点包含嘈杂的信息,那么将其知识传播到其他节点是不可靠的,甚至导致模型崩溃。在本文中,我们提出了Adanet:通过增强动态图神经网络的强化知识适应框架。与以前的方法相反,一旦添加了新链接,就立即更新邻居节点的嵌入方式,Adanet试图自适应地确定由于涉及的新链接而应更新哪些节点。考虑到是否更新一个邻居节点的嵌入的决定将对其他邻居节点产生很大的影响,因此,我们将节点更新的选择作为序列决策问题,并通过强化学习解决此问题。通过这种方式,我们可以将知识自适应地传播到其他节点,以学习健壮的节点嵌入表示。据我们所知,我们的方法构成了通过强化学习的动态图神经网络来探索强大知识适应的首次尝试。在三个基准数据集上进行的广泛实验表明,Adanet可以实现最新的性能。此外,我们通过在数据集中添加不同程度的噪声来执行实验,并定量和定性地说明ADANET的鲁棒性。
translated by 谷歌翻译
盲人面部修复(BFR)旨在从低品质的图像中恢复高质量的面部图像,并通常求助于面部先验,以改善恢复性能。但是,当前的方法仍然遇到两个主要困难:1)如何在不进行大规模调整的情况下得出强大的网络体系结构; 2)如何从一个网络中的多个面部先验捕获互补信息以提高恢复性能。为此,我们提出了一个面部修复搜索网络(FRSNET),以适应我们指定的搜索空间内的合适特征提取体系结构,这可以直接有助于恢复质量。在FRSNET的基础上,我们通过多个学习方案进一步设计了多个面部先验搜索网络(MFPSNET)。 MFPSNET最佳地从不同的面部先验中提取信息,并将信息融合到图像特征中,以确保保留外部指导和内部特征。通过这种方式,MFPSNet充分利用了语义级别(解析图),几何级别(面部热图),参考级别(面部词典)和像素级(降级图像)信息,从而产生忠实且逼真的图像。定量和定性实验表明,MFPSNET在合成和现实世界数据集上对最先进的BFR方法表现出色。这些代码可公开可用:https://github.com/yyj1ang/mfpsnet。
translated by 谷歌翻译
知识蒸馏(KD)证明了其有效性,可以提高图形神经网络(GNN)的性能,其目标是将知识从更深的教师gnn蒸馏成较浅的学生GNN。但是,由于众所周知的过度参数和过度光滑的问题,实际上很难培训令人满意的教师GNN,从而导致实际应用中的知识转移无效。在本文中,我们通过对GNN的加强学习(称为FreeKD)提出了第一个自由方向知识蒸馏框架,而这不再需要提供更深入的良好优化的教师GNN。我们工作的核心思想是协作建立两个较浅的GNN,以通过以层次结构方式通过加强学习来交流知识。正如我们观察到的一个典型的GNN模型在训练过程中通常在不同节点的表现更好,更差的表现,我们设计了一种动态和自由方向的知识转移策略,该策略由两个级别的动作组成:1)节点级别的动作决定了知识的方向。两个网络的相应节点之间的传输;然后2)结构级的动作确定了要传播的节点级别生成的局部结构。从本质上讲,我们的FreeKD是一个一般且原则性的框架,可以自然与不同架构的GNN兼容。在五个基准数据集上进行的广泛实验表明,我们的FreeKD在很大的边距上优于两个基本GNN,并显示了其对各种GNN的功效。更令人惊讶的是,我们的FreeKD比传统的KD算法具有可比性甚至更好的性能,这些KD算法将知识从更深,更强大的教师GNN中提取。
translated by 谷歌翻译
盲面修复(BFR)旨在从相应的低质量(LQ)输入中构建高质量(HQ)面部图像。最近,已经提出了许多BFR方法,并取得了杰出的成功。但是,这些方法经过私人合成的数据集进行了培训或评估,这使得与后续方法相比的方法是不可行的。为了解决这个问题,我们首先合成两个称为EDFEACE-CELEB-1M(BFR128)和EDFACE-CELEB-150K(BFR512)的盲面恢复基准数据集。在五个设置下,将最先进的方法在它们的五个设置下进行了基准测试,包括模糊,噪声,低分辨率,JPEG压缩伪像及其组合(完全退化)。为了使比较更全面,应用了五个广泛使用的定量指标和两个任务驱动的指标,包括平均面部标志距离(AFLD)和平均面部ID余弦相似性(AFICS)。此外,我们开发了一个有效的基线模型,称为Swin Transformer U-NET(昏迷)。带有U-NET体系结构的昏迷器应用了注意机制和移动的窗口方案,以捕获远程像素相互作用,并更多地关注重要功能,同时仍受到有效训练。实验结果表明,所提出的基线方法对各种BFR任务的SOTA方法表现出色。
translated by 谷歌翻译
最近深入学习已成功应用于无监督的主动学习。然而,当前方法试图通过自动编码器来忽略样本关系的同时学习非线性转换,留下巨大的空间来设计用于无监督的主动学习的更有效的表示学习机制。在本文中,我们通过可学习的图表提出了一种新颖的无监督的主动学习模型,命名为Allg。 allg从学习最佳图形结构中获益,以获取更好的样本表示,然后选择代表样本。为了使学习的图形结构更加稳定和有效,我们考虑了$ k $ -nealest邻居图作为先验,并学习关系传播图形结构。我们还将快捷方式连接到不同的层中,可以在一定程度上缓解众所周知的过平滑问题。据我们所知,这是第一次利用图形结构学习的第一次尝试,以便无监督的主动学习。在六个数据集上进行的广泛实验证明了我们的方法的功效。
translated by 谷歌翻译
Vision变形金刚(VITS)最近获得了爆炸性的人气,但巨额的计算成本仍然是一个严峻的问题。由于VIT的计算复杂性相对于输入序列长度是二次的,因此用于计算还原的主流范例是减少令牌的数量。现有设计包括结构化空间压缩,该压缩使用逐行缩小的金字塔来减少大型特征映射的计算,并且动态丢弃冗余令牌的非结构化令牌修剪。然而,现有令牌修剪的限制在两倍以下:1)由修剪引起的不完全空间结构与现代深窄变压器通常使用的结构化空间压缩不兼容; 2)通常需要耗时的预训练程序。为了解决局限性并扩大令牌修剪的适用场景,我们提出了Evo-Vit,一种自动激励的慢速令牌演化方法,用于视觉变压器。具体而言,我们通过利用原产于视觉变压器的简单有效的全球课程关注来进行非结构化的案例 - 明智的选择。然后,我们建议使用不同的计算路径更新所选的信息令牌和未表征性令牌,即慢速更新。由于快速更新机制保持空间结构和信息流,因此Evo-Vit可以从训练过程的开始,从训练过程的开始,加速平坦和深窄的结构的Vanilla变压器。实验结果表明,我们的方法显着降低了视觉变压器的计算成本,同时在图像分类上保持了可比性。
translated by 谷歌翻译
There is a growing interest in developing unlearnable examples (UEs) against visual privacy leaks on the Internet. UEs are training samples added with invisible but unlearnable noise, which have been found can prevent unauthorized training of machine learning models. UEs typically are generated via a bilevel optimization framework with a surrogate model to remove (minimize) errors from the original samples, and then applied to protect the data against unknown target models. However, existing UE generation methods all rely on an ideal assumption called label-consistency, where the hackers and protectors are assumed to hold the same label for a given sample. In this work, we propose and promote a more practical label-agnostic setting, where the hackers may exploit the protected data quite differently from the protectors. E.g., a m-class unlearnable dataset held by the protector may be exploited by the hacker as a n-class dataset. Existing UE generation methods are rendered ineffective in this challenging setting. To tackle this challenge, we present a novel technique called Unlearnable Clusters (UCs) to generate label-agnostic unlearnable examples with cluster-wise perturbations. Furthermore, we propose to leverage VisionandLanguage Pre-trained Models (VLPMs) like CLIP as the surrogate model to improve the transferability of the crafted UCs to diverse domains. We empirically verify the effectiveness of our proposed approach under a variety of settings with different datasets, target models, and even commercial platforms Microsoft Azure and Baidu PaddlePaddle.
translated by 谷歌翻译
Although significant progress has been made in few-shot learning, most of existing few-shot learning methods require supervised pre-training on a large amount of samples of base classes, which limits their generalization ability in real world application. Recently, large-scale self-supervised vision-language models (e.g., CLIP) have provided a new paradigm for transferable visual representation learning. However, the pre-trained VLPs may neglect detailed visual information that is difficult to describe by language sentences, but important for learning an effective classifier in few-shot classification. To address the above problem, we propose a new framework, named Semantic-guided Visual Adapting (SgVA), which can effectively extend vision-language pre-trained models to produce discriminative task-specific visual features by comprehensively using a vision-specific contrastive loss, a cross-modal contrastive loss, and an implicit knowledge distillation. The implicit knowledge distillation is designed to transfer the fine-grained cross-modal knowledge to guide the updating of the vision adapter. State-of-the-art results on 13 datasets demonstrate that the adapted visual features can well complement the cross-modal features to improve few-shot image classification.
translated by 谷歌翻译
Pre-trained Vision-Language Models (VLMs) such as CLIP have shown impressive generalization capability in downstream vision tasks with appropriate text prompts. Instead of designing prompts manually, Context Optimization (CoOp) has been recently proposed to learn continuous prompts using task-specific training data. Despite the performance improvements on downstream tasks, several studies have reported that CoOp suffers from the overfitting issue in two aspects: (i) the test accuracy on base classes first gets better and then gets worse during training; (ii) the test accuracy on novel classes keeps decreasing. However, none of the existing studies can understand and mitigate such overfitting problem effectively. In this paper, we first explore the cause of overfitting by analyzing the gradient flow. Comparative experiments reveal that CoOp favors generalizable and spurious features in the early and later training stages respectively, leading to the non-overfitting and overfitting phenomenon. Given those observations, we propose Subspace Prompt Tuning (SubPT) to project the gradients in back-propagation onto the low-rank subspace spanned by the early-stage gradient flow eigenvectors during the entire training process, and successfully eliminate the overfitting problem. Besides, we equip CoOp with Novel Feature Learner (NFL) to enhance the generalization ability of the learned prompts onto novel categories beyond the training set, needless of image training data. Extensive experiments on 11 classification datasets demonstrate that SubPT+NFL consistently boost the performance of CoOp and outperform the state-of-the-art approach CoCoOp. Experiments on more challenging vision downstream tasks including open-vocabulary object detection and zero-shot semantic segmentation also verify the effectiveness of the proposed method. Codes can be found at https://tinyurl.com/mpe64f89.
translated by 谷歌翻译
数字艺术合成在多媒体社区中受到越来越多的关注,因为有效地与公众参与了艺术。当前的数字艺术合成方法通常使用单模式输入作为指导,从而限制了模型的表现力和生成结果的多样性。为了解决这个问题,我们提出了多模式引导的艺术品扩散(MGAD)模型,该模型是一种基于扩散的数字艺术品生成方法,它利用多模式提示作为控制无分类器扩散模型的指导。此外,对比度语言图像预处理(剪辑)模型用于统一文本和图像模式。关于生成的数字艺术绘画质量和数量的广泛实验结果证实了扩散模型和多模式指导的组合有效性。代码可从https://github.com/haha-lisa/mgad-multimodal-guided-artwork-diffusion获得。
translated by 谷歌翻译