Deep transfer learning has been widely used for knowledge transmission in recent years. The standard approach of pre-training and subsequently fine-tuning, or linear probing, has shown itself to be effective in many down-stream tasks. Therefore, a challenging and ongoing question arises: how to quantify cross-task transferability that is compatible with transferred results while keeping self-consistency? Existing transferability metrics are estimated on the particular model by conversing source and target tasks. They must be recalculated with all existing source tasks whenever a novel unknown target task is encountered, which is extremely computationally expensive. In this work, we highlight what properties should be satisfied and evaluate existing metrics in light of these characteristics. Building upon this, we propose Principal Gradient Expectation (PGE), a simple yet effective method for assessing transferability across tasks. Specifically, we use a restart scheme to calculate every batch gradient over each weight unit more than once, and then we take the average of all the gradients to get the expectation. Thus, the transferability between the source and target task is estimated by computing the distance of normalized principal gradients. Extensive experiments show that the proposed transferability metric is more stable, reliable and efficient than SOTA methods.

视觉和听觉信息对于确定视频中的显着区域都是有价值的。深度卷积神经网络（CNN）展示了应对视听显着性预测任务的强大能力。由于各种因素，例如拍摄场景和天气，源训练数据和目标测试数据之间通常存在适度的分布差异。域差异导致CNN模型目标测试数据的性能降解。本文提前尝试解决视听显着性预测的无监督域适应问题。我们提出了一种双重域交流学习算法，以减轻源数据和目标数据之间的域差异。首先，建立了一个特定的域歧视分支，以对齐听觉功能分布。然后，这些听觉功能通过跨模式自我发项模块融合到视觉特征中。设计了其他域歧视分支，以减少视觉特征的域差异和融合视听特征所隐含的视听相关性的差异。公共基准测试的实验表明，我们的方法可以减轻域差异引起的性能降解。

弱监督的对象本地化是一项具有挑战性的任务，旨在将对象定位具有粗糙注释（例如图像类别）。现有的深网方法主要基于类激活图，该图的重点是突出显示歧视性局部区域，同时忽略了整个对象。此外，基于变压器的技术不断地重点放在阻碍识别完整对象的能力的背景上。为了解决这些问题，我们提出了一种称为令牌改进变压器（TRT）的重新注意事项机制，该机制捕获了对象级语义，以很好地指导本地化。具体而言，TRT引入了一个名为令牌优先级评分模块（TPSM）的新型模块，以抑制背景噪声的效果，同时重点放在目标对象上。然后，我们将类激活图作为语义意识的输入合并，以将注意力图限制为目标对象。在两个基准测试上进行的广泛实验展示了我们提出的方法与现有方法的优势，该方法具有带有图像类别注释的现有方法。源代码可在\ url {https://github.com/su-hui-zz/reattentiontransformer}中获得。

零件级别的属性解析是一项基本但具有挑战性的任务，它需要区域级的视觉理解以提供可解释的身体部位细节。大多数现有方法通过添加具有属性预测头到两阶段检测器的区域卷积神经网络（RCNN）来解决此问题，其中从本地零件框中确定了身体部位的属性。但是，具有极限视觉线索的本地零件框（即仅零件外观）会导致不满意的解析结果，因为身体部位的属性高度依赖于它们之间的全面关系。在本文中，我们建议通过利用丰富的知识来识别嵌入式RCNN（KE-RCNN）来识别属性-hip）和显式知识（例如，``短裤''的一部分不能具有``连帽衫''或``衬里''的属性）。具体而言，KE-RCNN由两个新型组件，即基于隐式知识的编码器（IK-en）和基于知识的显式解码器（EK-DE）组成。前者旨在通过将部分的关系上下文编码到部分框中来增强零件级的表示，而后者则建议通过有关\ textit {part-attribute}关系的先验知识的指导来解码属性。这样，KE-RCNN就是插件播放，可以集成到任何两阶段检测器中，例如attribute-rcnn，cascade-rcnn，基于HRNET的RCNN和基于Swintransformer的RCNN。在两个具有挑战性的基准上进行的广泛实验，例如Fashionpedia和Kinetics-TPS，证明了KE-RCNN的有效性和概括性。特别是，它比所有现有方法都取得了更高的改进，在时尚Pedia上达到了3％的AP，而动力学TPS的ACC约为4％。

部分一级的行动解析针对部分状态解析为影片提升动作识别。尽管在视频分类研究领域戏剧性的进展，面临的社会的一个严重问题是，人类活动的详细了解被忽略。我们的动机是，解析人的行动需要建立模型，专注于特定的问题。我们提出了一个简单而有效的方法，迎刃而解命名解析动作（DAP）。具体来说，我们划分部分一级行动解析为三个阶段：1）人的检测，当一个人检测器采用检测从影片的所有人员以及进行实例级动作识别; 2）部分解析，其中解析部分模型提出了识别来自检测到的人物图像人类份;和3）动作解析，其中，多模态动作解析网络用于分析动作类别调节对从先前阶段获得的所有检测结果。随着应用这三大车型，我们DAP的方法记录$ 0.605 $得分的全球平均在2021动力学-TPS挑战。

In the realm of multi-modality, text-guided image retouching techniques emerged with the advent of deep learning. Most currently available text-guided methods, however, rely on object-level supervision to constrain the region that may be modified. This not only makes it more challenging to develop these algorithms, but it also limits how widely deep learning can be used for image retouching. In this paper, we offer a text-guided mask-free image retouching approach that yields consistent results to address this concern. In order to perform image retouching without mask supervision, our technique can construct plausible and edge-sharp masks based on the text for each object in the image. Extensive experiments have shown that our method can produce high-quality, accurate images based on spoken language. The source code will be released soon.

Semantic segmentation based on sparse annotation has advanced in recent years. It labels only part of each object in the image, leaving the remainder unlabeled. Most of the existing approaches are time-consuming and often necessitate a multi-stage training strategy. In this work, we propose a simple yet effective sparse annotated semantic segmentation framework based on segformer, dubbed SASFormer, that achieves remarkable performance. Specifically, the framework first generates hierarchical patch attention maps, which are then multiplied by the network predictions to produce correlated regions separated by valid labels. Besides, we also introduce the affinity loss to ensure consistency between the features of correlation results and network predictions. Extensive experiments showcase that our proposed approach is superior to existing methods and achieves cutting-edge performance. The source code is available at \url{https://github.com/su-hui-zz/SASFormer}.

Significant progress has been made in learning image classification neural networks under long-tail data distribution using robust training algorithms such as data re-sampling, re-weighting, and margin adjustment. Those methods, however, ignore the impact of data imbalance on feature normalization. The dominance of majority classes (head classes) in estimating statistics and affine parameters causes internal covariate shifts within less-frequent categories to be overlooked. To alleviate this challenge, we propose a compound batch normalization method based on a Gaussian mixture. It can model the feature space more comprehensively and reduce the dominance of head classes. In addition, a moving average-based expectation maximization (EM) algorithm is employed to estimate the statistical parameters of multiple Gaussian distributions. However, the EM algorithm is sensitive to initialization and can easily become stuck in local minima where the multiple Gaussian components continue to focus on majority classes. To tackle this issue, we developed a dual-path learning framework that employs class-aware split feature normalization to diversify the estimated Gaussian distributions, allowing the Gaussian components to fit with training samples of less-frequent classes more comprehensively. Extensive experiments on commonly used datasets demonstrated that the proposed method outperforms existing methods on long-tailed image classification.

通过建立神经网络和内核方法之间的联系，无限宽度极限阐明了深度学习的概括和优化方面。尽管它们的重要性，但这些内核方法的实用性在大规模学习设置中受到限制，因为它们（超）二次运行时和内存复杂性。此外，大多数先前关于神经内核的作品都集中在relu激活上，这主要是由于其受欢迎程度，但这也是由于很难计算此类内核来进行一般激活。在这项工作中，我们通过提供进行一般激活的方法来克服此类困难。首先，我们编译和扩展激活功能的列表，该函数允许精确的双重激活表达式计算神经内核。当确切的计算未知时，我们提出有效近似它们的方法。我们提出了一种快速的素描方法，该方法近似于任何多种多层神经网络高斯过程（NNGP）内核和神经切线核（NTK）矩阵，以实现广泛的激活功能，这超出了常见的经过分析的RELU激活。这是通过显示如何使用任何所需激活函​​数的截短的Hermite膨胀来近似神经内核来完成的。虽然大多数先前的工作都需要单位球体上的数据点，但我们的方法不受此类限制的影响，并且适用于$ \ Mathbb {r}^d $中的任何点数据集。此外，我们为NNGP和NTK矩阵提供了一个子空间嵌入，具有接近输入的距离运行时和接近最佳的目标尺寸，该目标尺寸适用于任何\ EMPH {均质}双重激活功能，具有快速收敛的Taylor膨胀。从经验上讲，关于精确的卷积NTK（CNTK）计算，我们的方法可实现$ 106 \ times $速度，用于在CIFAR-10数据集上的5层默特网络的近似CNTK。

神经网络（NNS）和决策树（DTS）都是机器学习的流行模型，但具有相互排斥的优势和局限性。为了带来两个世界中的最好，提出了各种方法来明确或隐式地集成NN和DTS。在这项调查中，这些方法是在我们称为神经树（NTS）的学校中组织的。这项调查旨在对NTS进行全面审查，并尝试确定它们如何增强模型的解释性。我们首先提出了NTS的彻底分类学，该分类法表达了NNS和DTS的逐步整合和共同进化。之后，我们根据NTS的解释性和绩效分析，并建议解决其余挑战的可能解决方案。最后，这项调查以讨论有条件计算和向该领域的有希望的方向进行讨论结束。该调查中审查的论文列表及其相应的代码可在以下网址获得：https：//github.com/zju-vipa/awesome-neural-trees