Despite the recent visually-pleasing results achieved, the massive computational cost has been a long-standing flaw for diffusion probabilistic models (DPMs), which, in turn, greatly limits their applications on resource-limited platforms. Prior methods towards efficient DPM, however, have largely focused on accelerating the testing yet overlooked their huge complexity and sizes. In this paper, we make a dedicated attempt to lighten DPM while striving to preserve its favourable performance. We start by training a small-sized latent diffusion model (LDM) from scratch, but observe a significant fidelity drop in the synthetic images. Through a thorough assessment, we find that DPM is intrinsically biased against high-frequency generation, and learns to recover different frequency components at different time-steps. These properties make compact networks unable to represent frequency dynamics with accurate high-frequency estimation. Towards this end, we introduce a customized design for slim DPM, which we term as Spectral Diffusion (SD), for light-weight image synthesis. SD incorporates wavelet gating in its architecture to enable frequency dynamic feature extraction at every reverse steps, and conducts spectrum-aware distillation to promote high-frequency recovery by inverse weighting the objective based on spectrum magni tudes. Experimental results demonstrate that, SD achieves 8-18x computational complexity reduction as compared to the latent diffusion models on a series of conditional and unconditional image generation tasks while retaining competitive image fidelity.
translated by 谷歌翻译
MetaFormer, the abstracted architecture of Transformer, has been found to play a significant role in achieving competitive performance. In this paper, we further explore the capacity of MetaFormer, again, without focusing on token mixer design: we introduce several baseline models under MetaFormer using the most basic or common mixers, and summarize our observations as follows: (1) MetaFormer ensures solid lower bound of performance. By merely adopting identity mapping as the token mixer, the MetaFormer model, termed IdentityFormer, achieves >80% accuracy on ImageNet-1K. (2) MetaFormer works well with arbitrary token mixers. When specifying the token mixer as even a random matrix to mix tokens, the resulting model RandFormer yields an accuracy of >81%, outperforming IdentityFormer. Rest assured of MetaFormer's results when new token mixers are adopted. (3) MetaFormer effortlessly offers state-of-the-art results. With just conventional token mixers dated back five years ago, the models instantiated from MetaFormer already beat state of the art. (a) ConvFormer outperforms ConvNeXt. Taking the common depthwise separable convolutions as the token mixer, the model termed ConvFormer, which can be regarded as pure CNNs, outperforms the strong CNN model ConvNeXt. (b) CAFormer sets new record on ImageNet-1K. By simply applying depthwise separable convolutions as token mixer in the bottom stages and vanilla self-attention in the top stages, the resulting model CAFormer sets a new record on ImageNet-1K: it achieves an accuracy of 85.5% at 224x224 resolution, under normal supervised training without external data or distillation. In our expedition to probe MetaFormer, we also find that a new activation, StarReLU, reduces 71% FLOPs of activation compared with GELU yet achieves better performance. We expect StarReLU to find great potential in MetaFormer-like models alongside other neural networks.
translated by 谷歌翻译
Existing fine-tuning methods either tune all parameters of the pre-trained model (full fine-tuning), which is not efficient, or only tune the last linear layer (linear probing), which suffers a significant accuracy drop compared to the full fine-tuning. In this paper, we propose a new parameter-efficient fine-tuning method termed as SSF, representing that researchers only need to Scale and Shift the deep Features extracted by a pre-trained model to catch up with the performance of full fine-tuning. In this way, SSF also surprisingly outperforms other parameter-efficient fine-tuning approaches even with a smaller number of tunable parameters. Furthermore, different from some existing parameter-efficient fine-tuning methods (e.g., Adapter or VPT) that introduce the extra parameters and computational cost in the training and inference stages, SSF only adds learnable parameters during the training stage, and these additional parameters can be merged into the original pre-trained model weights via re-parameterization in the inference phase. With the proposed SSF, our model obtains 2.46% (90.72% vs. 88.54%) and 11.48% (73.10% vs. 65.57%) performance improvement on FGVC and VTAB-1k in terms of Top-1 accuracy compared to the full fine-tuning but only fine-tuning about 0.3M parameters. We also conduct amounts of experiments in various model families (CNNs, Transformers, and MLPs) and datasets. Results on 26 image classification datasets in total and 3 robustness & out-of-distribution datasets show the effectiveness of SSF. Code is available at https://github.com/dongzelian/SSF.
translated by 谷歌翻译
在多人2D姿势估计中,自下而上的方法同时预测了所有人的姿势,与自上而下的方法不同,不依赖于人类的检测。但是,与现有的自上而下方法相比,SOTA自下而上的方法的精度仍然不如较低。这是由于预测的人类姿势是根据不一致的人类边界箱中心进行回归的,并且缺乏人类规范的正常化,从而导致预测的人类姿势被遗漏了不准确和小规模的人。为了推动自下而上的姿势估计的信封,我们首先提出了多尺度训练,以增强网络以通过单尺度测试来处理规模变化,尤其是对于小规模的人。其次,我们介绍了双解剖中心(即头部和身体),在这里我们可以更准确,可靠地预测人类的姿势,尤其是对于小规模的人。此外,现有的自下而上方法采用多尺度测试来以多个额外的前向通行证的价格提高姿势估计的准确性,这削弱了自下而上方法的效率,与自上而下的方法相比,核心强度。相比之下,我们的多尺度训练使该模型能够预测单个前向通行证(即单尺度测试)中的高质量姿势。我们的方法在边界框的精度方面取得了38.4 \%的改进,在边界框上进行了39.1 \%的改进,以对可可的具有挑战性的小规模人群进行对现状(SOTA)的回忆(SOTA)。对于人类姿势AP评估,我们在带有单尺度测试的可可测试-DEV集中实现了新的SOTA(71.0 AP)。我们还在跨数据库评估中在Ochuman数据集上实现了最高的性能(40.3 AP)。
translated by 谷歌翻译
无监督的生成的虚拟人类具有各种外观和动画姿势对于创建3D人体化身和其他AR/VR应用非常重要。现有方法要么仅限于刚性对象建模,要么不生成,因此无法合成高质量的虚拟人类并使它们进行动画化。在这项工作中,我们提出了Avatargen,这是第一种不仅可以具有不同外观的非刚性人类产生的方法,而且还可以完全控制姿势和观点,同时仅需要2D图像进行训练。具体而言,它通过利用粗糙的人体模型作为代理将观察空间扭曲到规范空间下的标准头像,将最近的3D甘斯扩展到了人类的衣服。为了建模非刚性动力学,它引入了一个变形网络,以学习规范空间中的姿势依赖性变形。为了提高生成的人类化身的几何质量,它利用签名距离字段作为几何表示,从而可以从几何学学习上的身体模型中进行更直接的正则化。从这些设计中受益,我们的方法可以生成具有高质量外观和几何形状建模的动画人体化身,从而极大地表现了先前的3D gan。此外,它有能力用于许多应用,例如单视重构造,复活和文本引导的合成。代码和预培训模型将可用。
translated by 谷歌翻译
在本文中,我们探讨了一个新的知识障碍问题,称为联合选择性聚合(FEDSA)。 FEDSA的目的是在几位分散的教师的帮助下培训学生模型,以完成一项新任务,他们的预培训任务和数据是不同且不可知的。我们调查此类问题设置的动机源于最近的模型共享困境。许多研究人员或机构已经在培训大型且称职的网络上花费了巨大的资源。由于隐私,安全或知识产权问题,他们也无法分享自己的预培训模型,即使他们希望为社区做出贡献。拟议的FEDSA提供了解决这一困境的解决方案,并使其更进一步,因为学识渊博的学生可以专门从事与所有老师不同的新任务。为此,我们提出了一种处理FEDSA的专门战略。具体而言,我们的学生培训过程是由一种新型的基于显着性的方法驱动的,该方法可以适应教师作为参与者,并将其代表性能力融入到学生中。为了评估FEDSA的有效性,我们在单任务和多任务设置上进行实验。实验结果表明,FEDSA有效地将分散模型的知识融合在一起,并将竞争性能达到集中式基准。
translated by 谷歌翻译
异常检测旨在识别正常数据分布的偏差样本。对比学习提供了一种成功的样本表示方式,可以有效地歧视异常。但是,当在半监督环境下设置的训练中被未标记的异常样本污染时,当前基于对比的方法通常1)忽略训练数据之间的全面关系,导致次优的性能,2)需要微调,导致低效率的低效率。为了解决上述两个问题,在本文中,我们提出了一种新型的分层半监督对比学习(HSCL)框架,以抗污染异常检测。具体而言,HSCL分层调节了三个互补关系:样本到样本,样本到原型型和正常关系,通过对受污染数据的全面探索,扩大了正常样本和异常样本之间的歧视。此外,HSCL是一种端到端的学习方法,可以在不进行微调的情况下有效地学习判别性表示。 HSCL在多种方案中实现了最先进的性能,例如单级分类和跨数据库检测。广泛的消融研究进一步验证了每个考虑的关系的有效性。该代码可在https://github.com/gaoangw/hscl上找到。
translated by 谷歌翻译
最先进的参数和非参数样式转移方法容易导致由于全局统计的对准而导致的本地样式模式,或者由于补丁不匹配而导致的不愉快的人工制品。在本文中,我们研究了一种新型的半参数神经风格转移框架,可减轻参数和非参数风格的缺乏。我们方法的核心思想是使用图神经网络(GNN)建立准确且细粒的内容样式对应关系。为此,我们开发了一个详细的GNN模型,其中包含内容和样式的本地补丁作为图形顶点。然后,将样式转移过程建模为基于注意力的异质消息,以可学习的方式在样式和内容节点之间传递,从而导致本地补丁级别的自适应多一对一风格的相关性。此外,引入了详细的可变形图卷积操作,以进行跨尺度样式符合匹配。实验结果表明,所提出的半参数图像样式化方法可为具有挑战性的样式模式产生令人鼓舞的结果,从而保留了全球外观和精美的细节。此外,通过控制推理阶段的边缘数量,提出的方法还触发了新的功能,例如使用单个模型的多元化基于斑块的风格化。
translated by 谷歌翻译
终身学习旨在学习一系列任务,而无需忘记先前获得的知识。但是,由于隐私或版权原因,涉及的培训数据可能不是终身合法的。例如,在实际情况下,模型所有者可能希望不时启用或禁用特定任务或特定样本的知识。不幸的是,这种灵活的对知识转移的灵活控制在以前的增量或减少学习方法中,即使在问题设定的水平上也被忽略了。在本文中,我们探索了一种新颖的学习方案,称为学习,可回收遗忘(LIRF),该方案明确处理任务或特定于样本的知识去除和恢复。具体而言,LIRF带来了两个创新的方案,即知识存款和撤回,这使用户指定的知识从预先训练的网络中隔离开来,并在必要时将其注入。在知识存款过程中,从目标网络中提取了指定的知识并存储在存款模块中,同时保留了目标网络的不敏感或一般知识,并进一步增强。在知识提取期间,将带走知识添加回目标网络。存款和提取过程仅需在删除数据上对几个时期进行填充时期,从而确保数据和时间效率。我们在几个数据集上进行实验,并证明所提出的LIRF策略具有令人振奋的概括能力。
translated by 谷歌翻译
示例引导图像生成的一个关键挑战在于在输入图像和引导图像之间建立细粒度的对应关系。尽管结果有令人鼓舞,但先前的方法还是依赖于对计算每点匹配的密集关注的依赖。在本文中,我们提出了一个动态稀疏注意的变压器模型,称为动态稀疏变压器(Dynast),以实现具有优惠效率的优质匹配。我们方法的核心是一个新颖的动态注意事项单元,致力于涵盖最佳代币数量的差异。具体而言,Dynast利用变压器结构的多层性质,并以级联的方式执行动态注意力方案,以完善匹配结果并合成视觉上令人愉悦的输出。此外,我们还为Dynast引入了一个统一的培训目标,使其成为监督和无监督场景的广泛参考图像翻译框架。对三种应用,姿势引导的人形象产生,基于边缘的面部合成以及未变形的图像样式转移的广泛实验表明,朝代在本地细节中实现了卓越的性能,超过了最新的技术,同时降低了计算成本。我们的代码可从https://github.com/huage001/dynast获得
translated by 谷歌翻译